Papers › FlipNeRF: Flipped Reflection Rays for Few-shot Novel View Synthesis

FlipNeRF: Flipped Reflection Rays for Few-shot Novel View Synthesis

30 Jun 2023ICCV 2023 1arXiv:2306.17723archive 2025-07-28

Seunghyeon Seo, Yeonjin Chang, Nojun Kwak

Neural Radiance Field (NeRF) has been a mainstream in novel view synthesis with its remarkable quality of rendered images and simple architecture. Although NeRF has been developed in various directions improving continuously its performance, the necessity of a dense set of multi-view images still exists as a stumbling block to progress for practical application. In this work, we propose FlipNeRF, a novel regularization method for few-shot novel view synthesis by utilizing our proposed flipped reflection rays. The flipped reflection rays are explicitly derived from the input ray directions and estimated normal vectors, and play a role of effective additional training rays while enabling to estimate more accurate surface normals and learn the 3D geometry effectively. Since the surface normal and the scene depth are both derived from the estimated densities along a ray, the accurate surface normal leads to more exact depth estimation, which is a key factor for few-shot novel view synthesis. Furthermore, with our proposed Uncertainty-aware Emptiness Loss and Bottleneck Feature Consistency Loss, FlipNeRF is able to estimate more reliable outputs with reducing floating artifacts effectively across the different scene structures, and enhance the feature-level consistency between the pair of the rays cast toward the photo-consistent pixels without any additional feature extractor, respectively. Our FlipNeRF achieves the SOTA performance on the multiple benchmarks across all the scenarios.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 14 code samples harvested from 1 repository linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 14 samples from 1 repository, 13 ran (12 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

shawn615/FlipNeRF officialmentioned on GitHubjaxMITSyntology: 14 samples, 13 ran (1 instrument-failed) · 1 unverified 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

14 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
12ran
1unverified

Licence: 1 of the 14 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from shawn615/FlipNeRF. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

shawn615/FlipNeRF official repository 14 samples, 13 ran (1 instrument-failed) · 1 unverified
convert_to_ndc in 11 papers internal/datasets.py ran MIT (permissive) · 9bf161da38d57d6d · report fixture: signature origins:ndarray/3/float, directions:ndarray/3/float, focal:float/0/float, width:int/0/int, height:int/0/int, near:float/0/float, focaly:float/0/float · returned tuple · level recorded 2026-09-26
convolve2d internal/vis.py ran fingerprinted MIT (permissive) · f4d06208684a7a77 · report fixture: signature z:ArrayImpl/2/float, f:ArrayImpl/2/float · returned ArrayImpl · level recorded 2026-09-26
cosine_easing_window internal/models.py ran MIT (permissive) · e1581dc42bebcdf0 · report fixture: signature alpha:float/0/float, min_freq_log2:int/0/int, max_freq_log2:int/0/int · returned ArrayImpl · level recorded 2026-09-26
downsample in 59 papers internal/datasets.py ran MIT (permissive) · ccbd6b71ec7797a2 · report fixture: signature img:ndarray/3/int, factor:int/0/int, patch_size:int/0/int, mode:int/0/int · returned ndarray · level recorded 2026-09-26
file_exists in 8 papers internal/utils.py ran MIT (permissive) · c850aeef1fd46daa · report fixture: signature pth:str/0/str · returned bool · level recorded 2026-09-26
lift_gaussian in 6 papers internal/mip.py ran MIT (permissive) · bb2b40e01c7d28fe · report fixture: signature d:ArrayImpl/2/float, t_mean:ArrayImpl/1/float, t_var:ArrayImpl/1/float, r_var:ArrayImpl/1/float, diag:bool/0/bool · returned tuple · level recorded 2026-09-26
matmul in 24 papers internal/math.py ran MIT (permissive) · 0f92b856a4c7ffa0 · report fixture: signature a:ArrayImpl/2/float, b:ArrayImpl/2/float · returned ArrayImpl · level recorded 2026-09-26
matte internal/vis.py ran MIT (permissive) · 455c8847b4e49a17 · report fixture: signature vis:ArrayImpl/3/float, acc:ArrayImpl/2/float, dark:float/0/float, light:float/0/float, width:int/0/int · returned ArrayImpl · level recorded 2026-09-26
open_file in 10 papers internal/utils.py ran MIT (permissive) · ea51e10bd8ccc6c6 · report fixture: signature pth:str/0/str, mode:str/0/str · returned TextIOWrapper · level recorded 2026-09-26
pos_enc internal/mip.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 7bdd0bba05723abc · report fixture: signature x:ArrayImpl/3/float, min_deg:int/0/int, max_deg:int/0/int, append_identity:bool/0/bool · returned ArrayImpl · level recorded 2026-09-22
safe_cos in 5 papers internal/math.py ran fingerprinted MIT (permissive) · 7033f6fda964538a · report fixture: signature x:ArrayImpl/1/float · returned ArrayImpl · level recorded 2026-09-26
safe_trig_helper in 5 papers internal/math.py ran MIT (permissive) · 762b96fa7015de47 · report fixture: signature x:ArrayImpl/1/float, fn:callable/0/?, t:float/0/float · returned ArrayImpl · level recorded 2026-09-26
sinebow internal/vis.py ran MIT (permissive) · 048c1208fee6c6fe · report fixture: signature h:ArrayImpl/0/float · returned ArrayImpl · level recorded 2026-09-26
listdir in 12 papers internal/utils.py unverified MIT (permissive) · 0bc10c560cd1a9d0 · report

Tasks

3D geometryDepth EstimationNeRFNovel View Synthesis

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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