Do We Still Need Rotation-Invariant Architectures? A Statistical Robustness Benchmark for Point Cloud Classification
cs.CV, cs.LG
Submitted: 2026-11-02
Updated: 2026-11-02
Project page: https://abdullah-nasir-chowdhury.github.io/projects/wacv2027
Terminology
Sources
- ShapeNet: An Information-Rich 3D Model Repository
- Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions
- RobustPointSet: A Dataset for Benchmarking Robustness of Point Cloud Classifiers
- Rotation Perturbation Robustness in Point Cloud Analysis: A Perspective of Manifold Distillation
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs