Papers › GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis

GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis

5 Jul 2020NeurIPS 2020 12arXiv:2007.02442archive 2025-07-28

Katja Schwarz, Yiyi Liao, Michael Niemeyer, Andreas Geiger

While 2D generative adversarial networks have enabled high-resolution image synthesis, they largely lack an understanding of the 3D world and the image formation process. Thus, they do not provide precise control over camera viewpoint or object pose. To address this problem, several recent approaches leverage intermediate voxel-based representations in combination with differentiable rendering. However, existing methods either produce low image resolution or fall short in disentangling camera and scene properties, e.g., the object identity may vary with the viewpoint. In this paper, we propose a generative model for radiance fields which have recently proven successful for novel view synthesis of a single scene. In contrast to voxel-based representations, radiance fields are not confined to a coarse discretization of the 3D space, yet allow for disentangling camera and scene properties while degrading gracefully in the presence of reconstruction ambiguity. By introducing a multi-scale patch-based discriminator, we demonstrate synthesis of high-resolution images while training our model from unposed 2D images alone. We systematically analyze our approach on several challenging synthetic and real-world datasets. Our experiments reveal that radiance fields are a powerful representation for generative image synthesis, leading to 3D consistent models that render with high fidelity.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2007.02442")

Code

Syntology Ran 3 of 12 code samples harvested from 1 repository linked to this paper; 9 have no recorded run. Of those that ran: 1 ran · violated contract; 1 ran · fixture could not drive it; 1 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

autonomousvision/graf officialmentioned in paperpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

12 samples harvested; 3 ran; 0 honoured the contract we drafted; 9 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · violated contract
1ran · fixture could not drive it
1ran
9unverified

Licence: 0 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from autonomousvision/graf. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

normalize autonomousvision/graf/submodules/nerf_pytorch/load_llff.py official repository ran · violated contract fingerprinted MIT (permissive) · 1d6f8390d799f055 · report
pose_spherical autonomousvision/graf/submodules/nerf_pytorch/load_blender.py official repository ran MIT (permissive) · 8313c1fb69b28c8e · report
viewmatrix autonomousvision/graf/submodules/nerf_pytorch/load_llff.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · aa52acee18f54d38 · report
color_depth_map autonomousvision/graf/graf/utils.py official repository unverified MIT (permissive) · 71ec2a9308fa61f3 · report
count_trainable_parameters autonomousvision/graf/graf/utils.py official repository unverified MIT (permissive) · 7de1ceff1fdc469d · report
get_data autonomousvision/graf/graf/config.py official repository unverified MIT (permissive) · 856b87aabeff2342 · report
get_nsamples autonomousvision/graf/graf/utils.py official repository unverified MIT (permissive) · 4cbceee1eebaf6d4 · report
get_render_poses autonomousvision/graf/graf/config.py official repository unverified MIT (permissive) · 677c56fac6ae59a2 · report
load_blender_data autonomousvision/graf/submodules/nerf_pytorch/load_blender.py official repository unverified MIT (permissive) · 83ed66ae61279dbc · report
load_dv_data autonomousvision/graf/submodules/nerf_pytorch/load_deepvoxels.py official repository unverified MIT (permissive) · e69746042397f344 · report
ptstocam autonomousvision/graf/submodules/nerf_pytorch/load_llff.py official repository unverified MIT (permissive) · 36f5de7a0aae4a9b · report
update_config autonomousvision/graf/graf/config.py official repository unverified MIT (permissive) · 559fa10dfa807ea5 · report

Tasks

3D-Aware Image SynthesisImage GenerationNovel View SynthesisScene Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Scene Generation AVD GRAF FID 62.59 #2 of 3 Archive leaderboard report
Scene Generation AVD GRAF SwAV-FID 6.95 #2 of 3 Archive leaderboard report
Scene Generation Replica GRAF FID 65.37 #2 of 3 Archive leaderboard report
Scene Generation Replica GRAF SwAV-FID 5.76 #2 of 3 Archive leaderboard report
Scene Generation VizDoom GRAF FID 47.50 #2 of 3 Archive leaderboard report
Scene Generation VizDoom GRAF SwAV-FID 5.44 #2 of 3 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections