[{"data":1,"prerenderedAt":734},["ShallowReactive",2],{"method-nerf2020":3},{"method":4,"reference":55,"equipment":78,"figures":97,"results":98},{"id":5,"label":6,"shortName":7,"title":8,"year":9,"era":10,"cluster":11,"scope":12,"keyIdeaZh":13,"keyIdeaEn":14,"fulltextStatus":15,"publicationStatus":16,"recommendation":17,"constructionRelevance":18,"validationEnvironment":19,"strengths":22,"limitations":26,"sensors":33,"platform":35,"estimator":36,"association":37,"timeModel":38,"deskew":38,"loopClosure":39,"globalOptimization":39,"mapRepresentation":40,"prior":41,"outputGeometry":42,"compute":43,"codeUrl":44,"codeLicense":45,"relatedVersions":46},"nerf2020","Mildenhall et al., 2020","NeRF","NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis",2020,"recent","C09","map_representation_or_reconstruction","NeRF 以多層感知器（MLP）將三維位置與觀看方向映射為體密度與顏色，並透過可微分體積渲染（volume rendering）以多視角影像的光度誤差最佳化網路。方法本身不估計相機位姿，實景資料需先以 COLMAP 等 SfM 取得位姿與內參。幾何只隱含在密度場中，是後續神經隱式 SLAM 共用的表示與渲染原理。","Represents a scene as an MLP-based radiance field optimized from posed images via differentiable volume rendering; poses must be supplied (e.g., by COLMAP).","full_text_reviewed","peer_reviewed_published","background","原論文未涉及營建場景；營建應用證據需見後續研究，例如 [jeon2025_nerf_construction]。",[20,21],"simulation","public_benchmark",[23,24,25],"Highest PSNR and SSIM on all three datasets, e.g. 31.01 dB on Realistic Synthetic 360 and 26.50 dB on Real Forward-Facing (Table 1)","Compact scene model: 5 MB of network weights vs over 15 GB for LLFF on one synthetic scene (Sec. 6.3)","Positional encoding and view dependence give the largest gains in the ablation (Table 2)",[27,28,29,30,31,32],"Requires known camera poses\u002Fintrinsics; COLMAP used for real data (implementation paragraph)","Authors note further work is needed on efficient optimization and rendering (conclusion)","Optimization takes about 1 to 2 days per scene and rendering about 30 s per frame on a V100 (Sec. 5.3, App. A)","Expected quality and failure modes are hard to analyze when the scene is stored in network weights (Sec. 7)","Represents a static scene (Sec. 1, Sec. 3)","LLFF has better LPIPS on the real forward-facing data (0.212 vs 0.250) (Table 1)",[34],"monocular camera (multi-view images)",[],"not_applicable (per-scene gradient-based optimization of an MLP; camera poses are inputs)","direct photometric loss through differentiable volume rendering","not_applicable","none","neural implicit radiance field (MLP: volume density + view-dependent colour)","known camera poses, intrinsics and scene bounds (COLMAP SfM for real scenes)","Novel-view images; geometry only implicit in the density field; the paper reports no surface extraction and no geometric accuracy evaluation; real forward-facing scenes are optimized in normalized device coordinates that use disparity rather than metric depth (Sec. 3 to 6, App. A, App. C)","Per-scene optimization of 100k to 300k iterations on a single NVIDIA V100 GPU (about 1 to 2 days); rendering an image takes about 30 s on a V100 (150 to 200 million network queries); network weights 5 MB (Sec. 5.3, Sec. 6.3, App. A)","https:\u002F\u002Fgithub.com\u002Fbmild\u002Fnerf","MIT",[47,51],{"relation":48,"title":49,"doi_or_url":50},"preprint","arXiv:2003.08934","https:\u002F\u002Farxiv.org\u002Fabs\u002F2003.08934",{"relation":52,"title":53,"doi_or_url":54},"journal_extension","NeRF (Communications of the ACM 65(1):99-106, research highlight version)","10.1145\u002F3503250",{"id":5,"kind":56,"shortName":7,"title":8,"authors":57,"year":9,"venue":64,"venueType":65,"publisher":66,"volumeIssuePages":67,"doi":68,"arxivId":69,"url":70,"firstPublicDate":71,"publicationStatus":16,"metadataStatus":72,"fulltextStatus":15,"era":10,"classicReason":38,"codeUrl":44,"cluster":11,"topics":73,"mdpi":74,"verification":75,"label":6,"fulltextRoute":76,"versionRead":77,"addedByCensus":74},"method",[58,59,60,61,62,63],"Ben Mildenhall","Pratul P. Srinivasan","Matthew Tancik","Jonathan T. Barron","Ravi Ramamoorthi","Ren Ng","Computer Vision - ECCV 2020 (Lecture Notes in Computer Science)","conference","Springer","LNCS, pp. 405-421","10.1007\u002F978-3-030-58452-8_24","2003.08934","https:\u002F\u002Fapi.crossref.org\u002Fworks\u002F10.1007\u002F978-3-030-58452-8_24","2020-03-19","metadata_verified",[11],false,"confirmed","NTU institutional (curl)","Version of record (ECCV 2020, LNCS, pp. 405-421, Springer PDF) for the main paper, plus the arXiv v2 (2020-08-03) appendices A-D, which correspond to the VoR supplementary material; main text and Tables 1-2 identical in both",[79,86,93],{"category":80,"model":81,"canonical":81,"role":82,"dataset":83,"specs":84,"locator":85},"camera","handheld cellphone (model not named)","dataset sensor","Real Forward-Facing (5 LLFF scenes + 3 new)","forward-facing captures, 20 to 62 images per scene, 1008 x 756 pixels","Sec. 6.1; Table 1 caption",{"category":87,"model":88,"canonical":88,"role":89,"dataset":90,"specs":91,"locator":92},"compute","NVIDIA V100","compute for runtime",null,"single GPU; 100k to 300k iterations take about 1 to 2 days; about 30 s per rendered frame","Sec. 5.3; App. A",{"category":87,"model":94,"canonical":94,"role":89,"dataset":90,"specs":95,"locator":96},"4 NVIDIA V100 GPUs","needed to run the SRN baseline at 512 x 512","App. B",[],{"totalRows":99,"groupCount":100,"groups":101,"others":733},53,4,[102,303,590,692],{"slug":103,"group":104,"sourceId":5,"sourceLabel":6,"table":105,"selfRows":106,"metrics":107,"seqs":117,"entrants":136,"cells":144,"outcomes":296,"locators":297,"hardware":299,"wordings":300,"notes":301},"nerf2020-table-5","nerf2020:Table 5","Table 5",24,[108,112,115],{"label":109,"unit":110,"statistic":111,"alignment":39},"PSNR (higher is better)","dB","not_reported",{"label":113,"unit":114,"statistic":111,"alignment":39},"SSIM (higher is better)","unitless",{"label":116,"unit":114,"statistic":111,"alignment":39},"LPIPS (lower is better)",[118,122,124,126,128,130,132,134],{"dataset":119,"sequence":120,"environment":121},"Real Forward-Facing","Room","real scene, handheld cellphone, forward-facing",{"dataset":119,"sequence":123,"environment":121},"Fern",{"dataset":119,"sequence":125,"environment":121},"Leaves",{"dataset":119,"sequence":127,"environment":121},"Fortress",{"dataset":119,"sequence":129,"environment":121},"Orchids",{"dataset":119,"sequence":131,"environment":121},"Flower",{"dataset":119,"sequence":133,"environment":121},"T-Rex",{"dataset":119,"sequence":135,"environment":121},"Horns",[137,139,141],{"name":138,"methodId":90,"linkable":74,"proposed":74,"self":74},"SRN [42]",{"name":140,"methodId":90,"linkable":74,"proposed":74,"self":74},"LLFF [28]",{"name":142,"methodId":5,"linkable":143,"proposed":143,"self":143},"NeRF (Ours)",true,[145,149,152,155,157,159,161,163,165,167,170,172,174,176,178,180,183,185,187,190,192,194,197,199,201,203,205,207,209,211,213,215,217,219,221,223,225,227,229,231,233,235,237,239,241,243,245,247,249,251,253,255,257,259,261,263,265,267,269,271,273,275,276,278,280,282,284,286,288,290,292,294],[146,146,146,147,148,146,148,148,146],0,27.29,-1,[146,150,146,151,148,146,148,148,146],1,0.883,[146,153,146,154,148,146,148,148,146],2,0.24,[146,146,150,156,148,146,148,148,146],21.37,[146,150,150,158,148,146,148,148,146],0.611,[146,153,150,160,148,146,148,148,146],0.459,[146,146,153,162,148,146,148,148,146],18.24,[146,150,153,164,148,146,148,148,146],0.52,[146,153,153,166,148,146,148,148,146],0.44,[146,146,168,169,148,146,148,148,146],3,26.63,[146,150,168,171,148,146,148,148,146],0.641,[146,153,168,173,148,146,148,148,146],0.453,[146,146,100,175,148,146,148,148,146],17.37,[146,150,100,177,148,146,148,148,146],0.449,[146,153,100,179,148,146,148,148,146],0.467,[146,146,181,182,148,146,148,148,146],5,24.63,[146,150,181,184,148,146,148,148,146],0.738,[146,153,181,186,148,146,148,148,146],0.288,[146,146,188,189,148,146,148,148,146],6,22.87,[146,150,188,191,148,146,148,148,146],0.761,[146,153,188,193,148,146,148,148,146],0.298,[146,146,195,196,148,146,148,148,146],7,24.33,[146,150,195,198,148,146,148,148,146],0.742,[146,153,195,200,148,146,148,148,146],0.376,[150,146,146,202,148,146,148,148,146],28.42,[150,150,146,204,148,146,148,148,146],0.932,[150,153,146,206,148,146,148,148,146],0.155,[150,146,150,208,148,146,148,148,146],22.85,[150,150,150,210,148,146,148,148,146],0.753,[150,153,150,212,148,146,148,148,146],0.247,[150,146,153,214,148,146,148,148,146],19.52,[150,150,153,216,148,146,148,148,146],0.697,[150,153,153,218,148,146,148,148,146],0.216,[150,146,168,220,148,146,148,148,146],29.4,[150,150,168,222,148,146,148,148,146],0.872,[150,153,168,224,148,146,148,148,146],0.173,[150,146,100,226,148,146,148,148,146],18.52,[150,150,100,228,148,146,148,148,146],0.588,[150,153,100,230,148,146,148,148,146],0.313,[150,146,181,232,148,146,148,148,146],25.46,[150,150,181,234,148,146,148,148,146],0.844,[150,153,181,236,148,146,148,148,146],0.174,[150,146,188,238,148,146,148,148,146],24.15,[150,150,188,240,148,146,148,148,146],0.857,[150,153,188,242,148,146,148,148,146],0.222,[150,146,195,244,148,146,148,148,146],24.7,[150,150,195,246,148,146,148,148,146],0.84,[150,153,195,248,148,146,148,148,146],0.193,[153,146,146,250,148,146,148,148,146],32.7,[153,150,146,252,148,146,148,148,146],0.948,[153,153,146,254,148,146,148,148,146],0.178,[153,146,150,256,148,146,148,148,146],25.17,[153,150,150,258,148,146,148,148,146],0.792,[153,153,150,260,148,146,148,148,146],0.28,[153,146,153,262,148,146,148,148,146],20.92,[153,150,153,264,148,146,148,148,146],0.69,[153,153,153,266,148,146,148,148,146],0.316,[153,146,168,268,148,146,148,148,146],31.16,[153,150,168,270,148,146,148,148,146],0.881,[153,153,168,272,148,146,148,148,146],0.171,[153,146,100,274,148,146,148,148,146],20.36,[153,150,100,171,148,146,148,148,146],[153,153,100,277,148,146,148,148,146],0.321,[153,146,181,279,148,146,148,148,146],27.4,[153,150,181,281,148,146,148,148,146],0.827,[153,153,181,283,148,146,148,148,146],0.219,[153,146,188,285,148,146,148,148,146],26.8,[153,150,188,287,148,146,148,148,146],0.88,[153,153,188,289,148,146,148,148,146],0.249,[153,146,195,291,148,146,148,148,146],27.45,[153,150,195,293,148,146,148,148,146],0.828,[153,153,195,295,148,146,148,148,146],0.268,[],[298],"arXiv v2 App. D, Table 5",[],[],[302],"Per-scene novel-view synthesis metrics on the Real Forward-Facing dataset (8 scenes captured with a forward-facing handheld cellphone); SRN evaluated at 504 x 376, others at full resolution (appendix D).",{"slug":304,"group":305,"sourceId":306,"sourceLabel":307,"table":308,"selfRows":309,"metrics":310,"seqs":318,"entrants":355,"cells":371,"outcomes":581,"locators":584,"hardware":585,"wordings":587,"notes":588},"huang2024-2dgs-table-1","huang2024_2dgs:Table 1","huang2024_2dgs","Huang et al., 2024a","Table 1",17,[311,313,315],{"label":312,"unit":111,"statistic":111,"alignment":111},"Chamfer distance (CD)",{"label":312,"unit":111,"statistic":314,"alignment":111},"mean",{"label":316,"unit":317,"statistic":111,"alignment":39},"Time (training\u002Freconstruction time)","min",[319,323,325,327,329,331,333,335,337,339,341,343,345,347,349,351,353],{"dataset":320,"sequence":321,"environment":322},"DTU","scan 24","DTU: 15 scenes with 49 or 69 images at 1600 x 1200, downsampled to 800 x 600 (scene type not described in the paper)",{"dataset":320,"sequence":324,"environment":322},"scan 37",{"dataset":320,"sequence":326,"environment":322},"scan 40",{"dataset":320,"sequence":328,"environment":322},"scan 55",{"dataset":320,"sequence":330,"environment":322},"scan 63",{"dataset":320,"sequence":332,"environment":322},"scan 65",{"dataset":320,"sequence":334,"environment":322},"scan 69",{"dataset":320,"sequence":336,"environment":322},"scan 83",{"dataset":320,"sequence":338,"environment":322},"scan 97",{"dataset":320,"sequence":340,"environment":322},"scan 105",{"dataset":320,"sequence":342,"environment":322},"scan 106",{"dataset":320,"sequence":344,"environment":322},"scan 110",{"dataset":320,"sequence":346,"environment":322},"scan 114",{"dataset":320,"sequence":348,"environment":322},"scan 118",{"dataset":320,"sequence":350,"environment":322},"scan 122",{"dataset":320,"sequence":352,"environment":322},"Mean (15 scans)",{"dataset":320,"sequence":354,"environment":322},"all 15 scans",[356,358,360,362,365,367,369],{"name":357,"methodId":5,"linkable":143,"proposed":74,"self":143},"NeRF (Mildenhall et al., 2021)",{"name":359,"methodId":90,"linkable":74,"proposed":74,"self":74},"VolSDF (Yariv et al., 2021)",{"name":361,"methodId":90,"linkable":74,"proposed":74,"self":74},"NeuS (Wang et al., 2021)",{"name":363,"methodId":364,"linkable":143,"proposed":74,"self":74},"3DGS (Kerbl et al., 2023)","kerbl2023_3dgs",{"name":366,"methodId":90,"linkable":74,"proposed":74,"self":74},"SuGaR (Guédon and Lepetit, 2023)",{"name":368,"methodId":306,"linkable":143,"proposed":143,"self":74},"2DGS-15k (Ours)",{"name":370,"methodId":306,"linkable":143,"proposed":143,"self":74},"2DGS-30k (Ours)",[372,374,376,378,380,382,384,386,388,391,394,396,399,402,405,408,411,413,415,417,419,421,423,425,427,429,431,432,434,436,438,440,442,444,445,446,448,450,452,454,456,458,460,462,464,465,467,469,470,472,473,474,476,478,480,482,484,486,488,490,492,494,496,498,499,501,503,505,507,508,510,512,513,515,517,518,520,522,523,525,527,529,530,531,532,533,535,537,538,540,542,543,544,546,547,549,550,551,552,553,555,556,558,559,561,563,564,566,567,568,569,570,571,572,574,575,576,577,579],[146,146,146,373,148,146,148,148,146],1.9,[146,146,150,375,148,146,148,148,146],1.6,[146,146,153,377,148,146,148,148,146],1.85,[146,146,168,379,148,146,148,148,146],0.58,[146,146,100,381,148,146,148,148,146],2.28,[146,146,181,383,148,146,148,148,146],1.27,[146,146,188,385,148,146,148,148,146],1.47,[146,146,195,387,148,146,148,148,146],1.67,[146,146,389,390,148,146,148,148,146],8,2.05,[146,146,392,393,148,146,148,148,146],9,1.07,[146,146,395,287,148,146,148,148,146],10,[146,146,397,398,148,146,148,148,146],11,2.53,[146,146,400,401,148,146,148,148,146],12,1.06,[146,146,403,404,148,146,148,148,146],13,1.15,[146,146,406,407,148,146,148,148,146],14,0.96,[146,150,409,410,148,146,148,148,146],15,1.49,[146,153,412,90,146,146,146,148,146],16,[150,146,146,414,148,146,148,148,146],1.14,[150,146,150,416,148,146,148,148,146],1.26,[150,146,153,418,148,146,148,148,146],0.81,[150,146,168,420,148,146,148,148,146],0.49,[150,146,100,422,148,146,148,148,146],1.25,[150,146,181,424,148,146,148,148,146],0.7,[150,146,188,426,148,146,148,148,146],0.72,[150,146,195,428,148,146,148,148,146],1.29,[150,146,389,430,148,146,148,148,146],1.18,[150,146,392,424,148,146,148,148,146],[150,146,395,433,148,146,148,148,146],0.66,[150,146,397,435,148,146,148,148,146],1.08,[150,146,400,437,148,146,148,148,146],0.42,[150,146,403,439,148,146,148,148,146],0.61,[150,146,406,441,148,146,148,148,146],0.55,[150,150,409,443,148,146,148,148,146],0.86,[150,153,412,90,146,146,146,148,146],[153,146,146,150,148,146,148,148,146],[153,146,150,447,148,146,148,148,146],1.37,[153,146,153,449,148,146,148,148,146],0.93,[153,146,168,451,148,146,148,148,146],0.43,[153,146,100,453,148,146,148,148,146],1.1,[153,146,181,455,148,146,148,148,146],0.65,[153,146,188,457,148,146,148,148,146],0.57,[153,146,195,459,148,146,148,148,146],1.48,[153,146,389,461,148,146,148,148,146],1.09,[153,146,392,463,148,146,148,148,146],0.83,[153,146,395,164,148,146,148,148,146],[153,146,397,466,148,146,148,148,146],1.2,[153,146,400,468,148,146,148,148,146],0.35,[153,146,403,420,148,146,148,148,146],[153,146,406,471,148,146,148,148,146],0.54,[153,150,409,246,148,146,148,148,146],[153,153,412,90,146,146,146,148,146],[168,146,146,475,148,146,148,148,146],2.14,[168,146,150,477,148,146,148,148,146],1.53,[168,146,153,479,148,146,148,148,146],2.08,[168,146,168,481,148,146,148,148,146],1.68,[168,146,100,483,148,146,148,148,146],3.49,[168,146,181,485,148,146,148,148,146],2.21,[168,146,188,487,148,146,148,148,146],1.43,[168,146,195,489,148,146,148,148,146],2.07,[168,146,389,491,148,146,148,148,146],2.22,[168,146,392,493,148,146,148,148,146],1.75,[168,146,395,495,148,146,148,148,146],1.79,[168,146,397,497,148,146,148,148,146],2.55,[168,146,400,477,148,146,148,148,146],[168,146,403,500,148,146,148,148,146],1.52,[168,146,406,502,148,146,148,148,146],1.5,[168,150,409,504,148,146,148,148,146],1.96,[168,153,412,506,148,146,146,148,146],11.2,[100,146,146,385,148,146,148,148,146],[100,146,150,509,148,146,148,148,146],1.33,[100,146,153,511,148,146,148,148,146],1.13,[100,146,168,439,148,146,148,148,146],[100,146,100,514,148,146,148,148,146],2.25,[100,146,181,516,148,146,148,148,146],1.71,[100,146,188,404,148,146,148,148,146],[100,146,195,519,148,146,148,148,146],1.63,[100,146,389,521,148,146,148,148,146],1.62,[100,146,392,393,148,146,148,148,146],[100,146,395,524,148,146,148,148,146],0.79,[100,146,397,526,148,146,148,148,146],2.45,[100,146,400,528,148,146,148,148,146],0.98,[100,146,403,287,148,146,148,148,146],[100,146,406,524,148,146,148,148,146],[100,150,409,509,148,146,148,148,146],[100,153,412,90,150,146,146,148,146],[181,146,146,534,148,146,148,148,146],0.48,[181,146,150,536,148,146,148,148,146],0.92,[181,146,153,437,148,146,148,148,146],[181,146,168,539,148,146,148,148,146],0.4,[181,146,100,541,148,146,148,148,146],1.04,[181,146,181,463,148,146,148,148,146],[181,146,188,463,148,146,148,148,146],[181,146,195,545,148,146,148,148,146],1.36,[181,146,389,383,148,146,148,148,146],[181,146,392,548,148,146,148,148,146],0.76,[181,146,395,426,148,146,148,148,146],[181,146,397,519,148,146,148,148,146],[181,146,400,539,148,146,148,148,146],[181,146,403,548,148,146,148,148,146],[181,146,406,554,148,146,148,148,146],0.6,[181,150,409,463,148,146,148,148,146],[181,153,412,557,148,146,146,148,146],5.5,[188,146,146,534,148,146,148,148,146],[188,146,150,560,148,146,148,148,146],0.91,[188,146,153,562,148,146,148,148,146],0.39,[188,146,168,562,148,146,148,148,146],[188,146,100,565,148,146,148,148,146],1.01,[188,146,181,463,148,146,148,148,146],[188,146,188,418,148,146,148,148,146],[188,146,195,545,148,146,148,148,146],[188,146,389,383,148,146,148,148,146],[188,146,392,548,148,146,148,148,146],[188,146,395,424,148,146,148,148,146],[188,146,397,573,148,146,148,148,146],1.4,[188,146,400,539,148,146,148,148,146],[188,146,403,548,148,146,148,148,146],[188,146,406,164,148,146,148,148,146],[188,150,409,578,148,146,148,148,146],0.8,[188,153,412,580,148,146,146,148,146],10.9,[582,583],"reported as '>12h' (not a point value)","reported as '~1h' (not a point value)",[308],[586],"2DGS experiments on a single RTX 3090 (written 'GTX RTX3090'); hardware for baselines not stated",[],[589],"Chamfer distance per DTU scan (15 scans) and mean; meshes of 3DGS and 2DGS by TSDF fusion of rendered depth; unit not stated in the paper; images downsampled to 800 x 600; COLMAP sparse points for initialization",{"slug":591,"group":592,"sourceId":5,"sourceLabel":6,"table":308,"selfRows":392,"metrics":593,"seqs":597,"entrants":607,"cells":615,"outcomes":685,"locators":687,"hardware":688,"wordings":689,"notes":690},"nerf2020-table-1","nerf2020:Table 1",[594,595,596],{"label":109,"unit":110,"statistic":314,"alignment":39},{"label":113,"unit":114,"statistic":314,"alignment":39},{"label":116,"unit":114,"statistic":314,"alignment":39},[598,602,605],{"dataset":599,"sequence":600,"environment":601},"Diffuse Synthetic 360 (DeepVoxels)","average over scenes","synthetic diffuse objects",{"dataset":603,"sequence":600,"environment":604},"Realistic Synthetic 360","synthetic non-Lambertian objects",{"dataset":119,"sequence":600,"environment":606},"real scenes, handheld cellphone, forward-facing",[608,610,612,614],{"name":609,"methodId":90,"linkable":74,"proposed":74,"self":74},"SRN [41]",{"name":611,"methodId":90,"linkable":74,"proposed":74,"self":74},"NV [23]",{"name":613,"methodId":90,"linkable":74,"proposed":74,"self":74},"LLFF [27]",{"name":142,"methodId":5,"linkable":143,"proposed":143,"self":143},[616,618,620,622,624,626,628,630,632,634,636,638,640,642,644,646,647,648,649,651,653,655,657,659,661,663,665,667,669,671,673,675,677,679,681,683],[146,146,146,617,148,146,148,148,146],33.2,[146,150,146,619,148,146,148,148,146],0.963,[146,153,146,621,148,146,148,148,146],0.073,[146,146,150,623,148,146,148,148,146],22.26,[146,150,150,625,148,146,148,148,146],0.846,[146,153,150,627,148,146,148,148,146],0.17,[146,146,153,629,148,146,148,148,146],22.84,[146,150,153,631,148,146,148,148,146],0.668,[146,153,153,633,148,146,148,148,146],0.378,[150,146,146,635,148,146,148,148,146],29.62,[150,150,146,637,148,146,148,148,146],0.929,[150,153,146,639,148,146,148,148,146],0.099,[150,146,150,641,148,146,148,148,146],26.05,[150,150,150,643,148,146,148,148,146],0.893,[150,153,150,645,148,146,148,148,146],0.16,[150,146,153,90,146,146,148,148,146],[150,150,153,90,146,146,148,148,146],[150,153,153,90,146,146,148,148,146],[153,146,146,650,148,146,148,148,146],34.38,[153,150,146,652,148,146,148,148,146],0.985,[153,153,146,654,148,146,148,148,146],0.048,[153,146,150,656,148,146,148,148,146],24.88,[153,150,150,658,148,146,148,148,146],0.911,[153,153,150,660,148,146,148,148,146],0.114,[153,146,153,662,148,146,148,148,146],24.13,[153,150,153,664,148,146,148,148,146],0.798,[153,153,153,666,148,146,148,148,146],0.212,[168,146,146,668,148,146,148,148,146],40.15,[168,150,146,670,148,146,148,148,146],0.991,[168,153,146,672,148,146,148,148,146],0.023,[168,146,150,674,148,146,148,148,146],31.01,[168,150,150,676,148,146,148,148,146],0.947,[168,153,150,678,148,146,148,148,146],0.081,[168,146,153,680,148,146,148,148,146],26.5,[168,150,153,682,148,146,148,148,146],0.811,[168,153,153,684,148,146,148,148,146],0.25,[686],"not_applicable ('-')",[308],[],[],[691],"Novel-view synthesis quality: PSNR (dB) and SSIM higher is better, LPIPS lower is better; Diffuse Synthetic 360 (DeepVoxels, 4 objects, 479 input views), Realistic Synthetic 360 (8 path-traced objects, 100 input views), Real Forward-Facing (8 handheld cellphone scenes, 20 to 62 images, 1\u002F8 held out). NV cannot run on real forward-facing data ('-'); SRN metrics computed at lower resolution (512 x 512 synthetic, 504 x 376 real).",{"slug":693,"group":694,"sourceId":5,"sourceLabel":6,"table":695,"selfRows":168,"metrics":696,"seqs":706,"entrants":715,"cells":717,"outcomes":722,"locators":724,"hardware":728,"wordings":730,"notes":731},"nerf2020-text-sec-5-3-6-3-app-a","nerf2020:Text Sec.5.3, 6.3, App. A","Text Sec.5.3, 6.3, App. A",[697,700,703],{"label":698,"unit":699,"statistic":111,"alignment":39},"optimization time per scene (100k to 300k iterations)","days",{"label":701,"unit":702,"statistic":111,"alignment":39},"rendering time per frame (approximately)","s",{"label":704,"unit":705,"statistic":111,"alignment":39},"storage for network weights","MB",[707,710,713],{"dataset":708,"sequence":709,"environment":111},"per scene","typical scene",{"dataset":711,"sequence":712,"environment":111},"Realistic Synthetic 360 and Real Forward-Facing","rendering one image",{"dataset":708,"sequence":714,"environment":111},"network weights",[716],{"name":7,"methodId":5,"linkable":143,"proposed":143,"self":143},[718,719,721],[146,146,146,90,146,146,146,148,146],[146,150,150,720,148,150,150,148,146],30,[146,153,153,181,148,153,148,148,146],[723],"stated as about 1-2 days per scene",[725,726,727],"Sec. 5.3","App. A Rendering Details","Sec. 6.3",[729,88],"single NVIDIA V100 GPU",[],[732],"Optimization, rendering and storage cost of NeRF as stated in the text.",[],1790510665438]