Lune

CVPR2026Top-tier venue

From Rays to Projections: Better Inputs for Feed-Forward View Synthesis

Zirui Wu, Zeren Jiang, Martin R. Oswald, Jie Song

Abstract

Feed-forward view synthesis models predict a novel view in a single pass with minimal 3D inductive bias. Existing works encode cameras as Plücker ray maps, which tie predictions to the arbitrary world coordinate gauge and make them sensitive to small camera transformations, thereby undermining geometric consistency. In this paper, we ask what inputs best condition a model for robust and consistent view synthesis. We propose projective conditioning, which replaces raw camera parameters with a target-view projective cue that provides a stable 2D input. This reframes the task from a brittle geometric regression problem in ray space to a well-conditioned target-view image-to-image translation problem. Additionally, we introduce a masked autoencoding pretraining strategy tailored to this cue, enabling the use of large-scale uncalibrated data for pretraining. Our method shows improved fidelity and stronger cross-view consistency compared to ray-conditioned baselines on our view-consistency benchmark. It also achieves state-of-the-art quality on standard novel view synthesis benchmarks.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Cameras as Relative Positional Encoding cites Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on19

  1. 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 5,687 citations
  2. Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance FieldsJonathan T. Barron, Ben Mildenhall, Dor Verbin, Pratul P. Srinivasan et al.ICCV 2023 · 799 citations
  3. DUSt3R: Geometric 3D Vision Made EasyShuzhe Wang, Vincent Leroy, Yohann Cabon, Boris Chidlovskii et al.CVPR 2024 · 302 citations
  4. Diffusion Transformers with Representation AutoencodersBoyang Zheng, Nanye Ma, Shengbang Tong, Saining XieICLR 2026 · 288 citations
  5. Cameras as Relative Positional EncodingRuilong Li, Brent Yi, Junchen Liu, Hang Gao et al.NeurIPS 2025 · 113 citations

Related papers

  1. Zero-1-to-3: Zero-shot One Image to 3D ObjectRuoshi Liu, Rundi Wu, Basile Van Hoorick, Pavel Tokmakov et al.ICCV 2023 · 1,662 citations
  2. SemanticNVS: Improving Semantic Scene Understanding in Generative Novel View SynthesisXinya Chen, Christopher Wewer, Jiahao Xie, Xinting Hu et al.ICML 2026
  3. Ray Conditioning: Trading Photo-consistency for Photo-realism in Multi-view Image GenerationEric Ming Chen, Sidhanth Holalkere, Ruyu Yan, Kai Zhang et al.ICCV 2023 · 11 citations
  4. Camera Pose Matters: Improving Depth Prediction by Mitigating Pose Distribution BiasYunhan Zhao, Shu Kong, Charless C. FowlkesCVPR 2021
  5. SparseGNV: Generating Novel Views of Indoor Scenes with Sparse RGB-D ImagesWeihao Cheng, Yan-Pei Cao, Ying ShanAAAI 2024 · 2 citations
Dusk over the sea between two cliffs drawn in fine vertical lines