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

arXiv:2601.05116 · cs.CV · Submitted 2026-01-08 · Read on arXiv

cs.CV

Submitted: 2026-01-08

Updated: 2026-01-08

Comments: Project Page: https://wuzirui.github.io/pvsm-web

Journal ref: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026, pp. 29012-29022

Project page: https://wuzirui.github.io/pvsm-web

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Consistency — 3× in this paper · explained in 3 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Inductive Bias — 1× in this paper · explained in 3 episodes

Sources

• Objaverse: A Universe of Annotated 3D Objects
• Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control
• MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• RayZer: A Self-supervised Large View Synthesis Model
• AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views
• MapAnything: Universal Feed-Forward Metric 3D Reconstruction
• Cameras as Relative Positional Encoding
• WorldMirror: Universal 3D World Reconstruction with Any-Prior Prompting
• Blending Distributed NeRFs with Tri-stage Robust Pose Optimization
• GS-Occ3D: Scaling Vision-only Occupancy Reconstruction with Gaussian Splatting
• DINOv3
• Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs
• RoFormer: Enhanced Transformer with Rotary Position Embedding
• Attention Is All You Need
• The Less You Depend, The More You Learn: Synthesizing Novel Views from Sparse, Unposed Images with Minimal 3D Knowledge
• CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion
• 3D Gaussian Inverse Rendering with Approximated Global Illumination
• Spectrally Pruned Gaussian Fields with Neural Compensation
• No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models