PCM-NeRF: Probabilistic Camera Modeling for Neural Radiance Fields under Pose Uncertainty

arXiv:2604.17831v1 Announce Type: new Abstract: Neural surface reconstruction methods typically treat camera poses as fixed values, assuming perfect accuracy from Structure-from-Motion (SfM) systems. This assumption breaks down with imperfect pose estimates, leading to distorted or incomplete reconstructions. We present PCM-NeRF, a probabilistic framework that augments neural surface reconstruction with per-camera learnable uncertainty, built on top of SG-NeRF. Rather than treating all cameras equally throughout optimization, we represent each pose as a distribution with a learnable mean and variance, initialized from SfM correspondence quality. An uncertainty regularization loss couples the learned variance to view confidence, and the resulting uncertainty directly modulates the effective pose learning rate: uncertain cameras receive damped gradient updates, preventing poorly initialized views from corrupting the reconstruction. This lightweight mechanism requires no changes to the rendering pipeline and adds negligible overhead. Experiments on challenging scenes with severe pose outliers demonstrate that PCM-NeRF consistently outperforms state-of-the-art methods in both Chamfer Distance and F-Score, particularly for geometrically complex structures, without requiring foreground masks.

Related

• A Comparison of Multi-View Stereo Methods for Photogrammetric 3D Reconstruction: From Traditional to Learning-Based Approaches
• Geometric Context Transformer for Streaming 3D Reconstruction
• Neural 3D Reconstruction of Planetary Surfaces from Descent-Phase Wide-Angle Imagery
• Privacy-Preserving Structureless Visual Localization via Image Obfuscation
• Neural Gabor Splatting: Enhanced Gaussian Splatting with Neural Gabor for High-frequency Surface Reconstruction
• GEAR: GEometry-motion Alternating Refinement for Articulated Object Modeling with Gaussian Splatting

Source: arXiv cs.CV | 2026-04-21