Browse State-of-the-Art › Novel View Synthesis

Novel View Synthesis

579 papers with code · 24 benchmarks · 46 datasets archive 2025-07-28

Computer Vision

Synthesize a target image with an arbitrary target camera pose from given source images and their camera poses.

See Wiki for more introductions.

The Synthesis method include: NeRF, MPI and so on.

( Image credit: Multi-view to Novel view: Synthesizing novel views with Self-Learned Confidence )

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

24 leaderboard tables shown for this task, 24 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 24 until expanded.

Syntology 16 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 6 placed): LLFF (2 judged, 0 placed), Mip-NeRF 360 (7 judged, 3 placed), NeRF (2 judged, 0 placed), Tanks and Temples (1 judged, 0 placed), ScanNet++ (1 judged, 0 placed), ACID (2 judged, 1 placed), RealEstate10K (5 judged, 1 placed), Deep Blending (5 judged, 2 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
LLFF (15 rows) TensoRF + NeRFLiX NeRFLiX: High-Quality Neural View Synthesis by Learning a... code — Compare
Mip-NeRF 360 (14 rows) MVGS MVGS: Multi-view-regulated Gaussian Splatting for Novel View Synthesis code Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified Compare
NeRF (12 rows) Deformable Beta Splatting Deformable Beta Splatting code Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified Compare
Tanks and Temples (10 rows) TensoRF + NeRFLiX++ From NeRFLiX to NeRFLiX++: A General NeRF-Agnostic Restorer Paradigm code — Compare
RefRef (8 rows) R3F-Oracle RefRef: A Synthetic Dataset and Benchmark for Reconstructing... code — Compare
DONeRF: Evaluation Dataset (6 rows) HyperReel HyperReel: High-Fidelity 6-DoF Video with Ray-Conditioned Sampling code Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified Compare
X3D (6 rows) SAX-NeRF Structure-Aware Sparse-View X-ray 3D Reconstruction code Syntology official (archive's flag): 2 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified Compare
RTMV (4 rows) Pixel-NeRF (env: Google Scan) RTMV: A Ray-Traced Multi-View Synthetic Dataset for Novel View Synthesis — — Compare
ScanNet++ (4 rows) 3DGEER 3DGEER: Exact and Efficient Volumetric Rendering with 3D Gaussians code — Compare
ACID (3 rows) impl.-nodepth Geometry-Free View Synthesis: Transformers and no 3D Priors code Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified Compare
BLEFF (3 rows) NeRFtrinsic Four NeRFtrinsic Four: An End-To-End Trainable NeRF Jointly Optimizing... code — Compare
SWORD (3 rows) StereoLayers (8 layers) Stereo Magnification with Multi-Layer Images — — Compare
HDR-GS (2 rows) HDR-GS HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x... code Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified Compare
iFF (2 rows) NeRFtrinsic Four NeRFtrinsic Four: An End-To-End Trainable NeRF Jointly Optimizing... code — Compare
RealEstate10K (2 rows) Hybrid Geometry-Free View Synthesis: Transformers and no 3D Priors code Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified Compare
. (1 row) Gear-NeRF Gear-NeRF: Free-Viewpoint Rendering and Tracking with Motion-aware... code Syntology 10 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 8 where Syntology's instrument failed) · 7 unverified Compare
Deep Blending (1 row) Self-Organizing Gaussians Compact 3D Scene Representation via Self-Organizing Gaussian Grids code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified Compare
Dosovitskiy Chairs (1 row) Single NeRF + Share./Inst. Net Editing Conditional Radiance Fields code Syntology official (archive's flag): 2 ran · 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result Compare
KITTI (1 row) READ READ: Large-Scale Neural Scene Rendering for Autonomous Driving code — Compare
KITTI Novel View Synthesis (1 row) Multi-view to Novel View Multi-view to Novel view: Synthesizing Novel Views with... code — Compare
PhotoShape (1 row) Single NeRF + Share./Inst. Net Editing Conditional Radiance Fields code Syntology official (archive's flag): 2 ran · 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result Compare
ShapeNet Car (1 row) Multi-view to Novel View Multi-view to Novel view: Synthesizing Novel Views with... code — Compare
ShapeNet Chair (1 row) Multi-view to Novel View Multi-view to Novel view: Synthesizing Novel Views with... code — Compare
Synthia Novel View Synthesis (1 row) Multi-view to Novel View Multi-view to Novel view: Synthesizing Novel Views with... code — Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

46 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 46 until expanded.

Subtasks archive 2025-07-28

2 subtasks in the archive's task tree.

Papers archive 2025-07-28

archive papers tagged: 1,441 · with a code link: 579 · where Syntology ran a sample: 250 (218 with a run with no instrument failure, 32 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (250 of 1,441 tagged: 218 with a run with no instrument failure, 32 where every run was a failure of Syntology's instrument)

Page 1 of 15: papers 1 to 100 of 1,441, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

Syntology lines on 44 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

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