Papers › Geometry-Free View Synthesis: Transformers and no 3D Priors

Geometry-Free View Synthesis: Transformers and no 3D Priors

15 Apr 2021ICCV 2021 10arXiv:2104.07652archive 2025-07-28

Robin Rombach, Patrick Esser, Björn Ommer

Is a geometric model required to synthesize novel views from a single image? Being bound to local convolutions, CNNs need explicit 3D biases to model geometric transformations. In contrast, we demonstrate that a transformer-based model can synthesize entirely novel views without any hand-engineered 3D biases. This is achieved by (i) a global attention mechanism for implicitly learning long-range 3D correspondences between source and target views, and (ii) a probabilistic formulation necessary to capture the ambiguity inherent in predicting novel views from a single image, thereby overcoming the limitations of previous approaches that are restricted to relatively small viewpoint changes. We evaluate various ways to integrate 3D priors into a transformer architecture. However, our experiments show that no such geometric priors are required and that the transformer is capable of implicitly learning 3D relationships between images. Furthermore, this approach outperforms the state of the art in terms of visual quality while covering the full distribution of possible realizations. Code is available at https://git.io/JOnwn

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="2104.07652")

Code

Syntology Ran 7 of 9 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · violated contract; 3 ran · our draft was wrong; 1 ran · fixture could not drive it; 1 ran with no contract checked.

By repository: official repository: 9 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

CompVis/geometry-free-view-synthesis officialmentioned on GitHubpytorchMIT 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

9 samples harvested; 7 ran; 1 honoured the contract we drafted; 2 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 · honoured contract
1ran · violated contract
3ran · our draft was wrong
1ran · fixture could not drive it
1ran
2unverified

Licence: 0 of the 9 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 CompVis/geometry-free-view-synthesis. “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 CompVis/geometry-free-view-synthesis/geofree/modules/diffusionmodules/model.py official repository ran · our draft was wrong MIT (permissive) · c3a6b977022957cb · report
count_params CompVis/geometry-free-view-synthesis/geofree/modules/util.py official repository ran · honoured contract MIT (permissive) · 613acd72145a95f2 · report
disabled_train CompVis/geometry-free-view-synthesis/geofree/models/transformers/geogpt.py official repository ran · violated contract MIT (permissive) · 4cb732f513d69dfd · report
get_timestep_embedding CompVis/geometry-free-view-synthesis/geofree/modules/diffusionmodules/model.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · cb49209c125de1b4 · report
nonlinearity CompVis/geometry-free-view-synthesis/geofree/modules/diffusionmodules/model.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 3137073275f8c21a · report
sample CompVis/geometry-free-view-synthesis/geofree/modules/transformer/mingpt.py official repository ran MIT (permissive) · 958673f09e3e1cd0 · report
top_k_logits CompVis/geometry-free-view-synthesis/geofree/modules/transformer/mingpt.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 0f0021cdea13e4da · report
md5_hash CompVis/geometry-free-view-synthesis/geofree/util.py official repository unverified MIT (permissive) · c8d9d38b144e401f · report
to_rgb CompVis/geometry-free-view-synthesis/geofree/modules/util.py official repository unverified MIT (permissive) · dac48a57235412bf · report

Tasks

Novel View Synthesis

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Novel View Synthesis ACID impl.-nodepth FID 42.88 #1 of 3 Archive leaderboard report
Novel View Synthesis ACID hybrid NLL 5.341 #2 of 3 Archive leaderboard report
Novel View Synthesis ACID hybrid PSIM 2.83 #2 of 3 Archive leaderboard report
Novel View Synthesis ACID hybrid PSNR 15.54 #2 of 3 Archive leaderboard report
Novel View Synthesis ACID impl.-catdepth SSIM 0.42 #3 of 3 Archive leaderboard report
Novel View Synthesis RealEstate10K Hybrid FID 48.84 #1 of 2 Archive leaderboard report
Novel View Synthesis RealEstate10K Hybrid PSNR 12.51 #1 of 2 Archive leaderboard report
Novel View Synthesis RealEstate10K Impl.-depth NLL 4.836 #2 of 2 Archive leaderboard report
Novel View Synthesis RealEstate10K Impl.-depth PSIM 3.05 #2 of 2 Archive leaderboard report
Novel View Synthesis RealEstate10K Impl.-depth SSIM 0.44 #2 of 2 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