Abstract Rendering: Certified Rendering Under 3D Semantic Uncertainty

NeurIPSSpotlight2025

Authors: Chenxi Ji, Yangge Li, Xiangru Zhong, Huan Zhang, Sayan Mitra
Venue: NeurIPS 2025
Track: Spotlight

TL;DR

Rendering produces 2D images from 3D scene representations, yet how continuous variations in camera pose and scenes influence these images—and, consequently, downstream visual models—remains underexpl…

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

Topics

uncertainty 3d

← All NeurIPS 2025 Spotlight papers · Browse the whole archive