Geometric Collapse: When Vision Models Fail to Verify Physical Causality

• URL: http://arxiv.org/abs/2607.06871v1
• Date: Wed, 08 Jul 2026 00:04:02 GMT
• Title: Geometric Collapse: When Vision Models Fail to Verify Physical Causality
• Abstract summary: We propose Scrambled Edges, a controlled counterfactual that injects salient edge-like cues.<n>With energy-matched and structure-matched controls, we isolate the effect of unsupported edge evidence from high-frequency energy and edge sparsity.<n>Across CNN/ViT/SSL depth predictors, Scrambled Edges induce up to 3.2x larger deviation from clean predictions than energy-matched noise.
• Score: 52.43819179934414
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent progress in large-scale self-supervised learning has improved dense geometric prediction, but it remains unclear whether such scaling yields inference-time physical plausibility checks. We propose Scrambled Edges, a controlled counterfactual that injects salient edge-like cues while violating surface continuity, illumination coherence, and occlusion ordering. With energy-matched and structure-matched controls, we isolate the effect of unsupported edge evidence from high-frequency energy and edge sparsity. Across CNN/ViT/SSL depth predictors on NYU Depth v2 and KITTI, Scrambled Edges induce up to 3.2x larger deviation from clean predictions than energy-matched noise; additional diffusion and flow-matching depth estimators show attenuated but still significant collapse. The resulting Geometric Collapse propagates globally: even with oracle knowledge of the corrupted region, output-level repair recovers only 47%, with substantial error outside the mask. These findings provide controlled behavioral evidence that current dense predictors lack reliable mechanisms to quarantine physically unsupported edge cues, motivating explicit plausibility scoring and selective cue integration.

Related papers

• Hidden Axis of Uncertainty: Latent-Posterior Alignment in Graph Neural Networks with Bayesian Output Layers [2.308349143406933]
  We study uncertainty dynamics in Graph Neural Networks (GNNs) with mean-field Bayesian output layers.<n>We observe that predictive uncertainty decreases as latent representations shift toward lower-variance posterior directions.<n>We propose Alignment-Guided Learning (AGL) which explicitly promotes this alignment during training.
  arXiv  Detail & Related papers  (2026-08-21T05:39:26Z)
• The impact of observation density on Bayesian inversion of latent dynamics in shock-dominated flows [0.6008132390640294]
  Inferring unknown initial states in shock-dominated compressible flows from sparse and noisy measurements is a challenging inverse problem.<n>We develop a non-intrusive reduced-order modeling framework for efficient Bayesian initial-state inversion with uncertainty.
  arXiv  Detail & Related papers  (2026-05-18T20:05:52Z)
• ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop [55.468404995694975]
  We develop a benchmark for embodied spatial intelligence spanning 10 task categories and 29 subcategories built on OmniGibson.<n>We conduct experiments on state-of-the-art MLLMs and find that active exploration substantially outperforms passive counterparts.<n>Unlike humans who seek falsifying viewpoints and revise beliefs under contradiction, models commit prematurely with high confidence regardless of evidence quality.
  arXiv  Detail & Related papers  (2026-05-18T17:59:02Z)
• DOC-GS: Dual-Domain Observation and Calibration for Reliable Sparse-View Gaussian Splatting [80.43237927269575]
  In this paper, we revisit sparse-view 3DGS reconstruction from a new perspective.<n>We identify the core challenge as the unobservability of Gaussian primitive reliability.<n>Motivated by this observation, we propose a unified Dual-domain Observation and geometrics in rendered images framework.
  arXiv  Detail & Related papers  (2026-04-08T07:01:24Z)
• Neural Uncertainty Principle: A Unified View of Adversarial Fragility and LLM Hallucination [60.197429875410286]
  Adversarial vulnerability in vision and hallucination in large language models are conventionally viewed as separate problems.<n>Formalizing a Neural Uncertainty Principle (NUP) under a loss-induced state, we find that in near-bound regimes, further compression must be accompanied by increased sensitivity dispersion.<n>In vision, masking highly coupled components improves robustness without costly adversarial training.<n>In language, the same prefill-stage probe detects hallucination risk before generating any answer tokens.
  arXiv  Detail & Related papers  (2026-03-20T02:07:10Z)
• The Phenomenology of Hallucinations [2.5782420501870296]
  We show that language models hallucinate not because they fail to detect uncertainty, but because of a failure to integrate it into output generation.<n>Across architectures, uncertain inputs are reliably identified, occupying high-dimensional regions with 2-3$times$ the intrinsic dimensionality of factual inputs.<n>However, this internal signal is weakly coupled to the output layer: uncertainty migrates into low-sensitivity subspaces, becoming geometrically amplified yet functionally silent.
  arXiv  Detail & Related papers  (2026-03-14T11:55:55Z)
• Uncertainty-Aware 4D Gaussian Splatting for Monocular Occluded Human Rendering [20.390068289144484]
  We propose U-4DGS, a framework integrating a Probabilistic Deformation Network and a Double Rasterization pipeline.<n>This architecture renders pixel-aligned uncertainty maps that act as an adaptive modulator, automatically attenuating artifacts from unreliable observations.<n>Experiments on ZJU-MoCap and OcMotion demonstrate that U-4DGS achieves SOTA rendering fidelity and robustness.
  arXiv  Detail & Related papers  (2026-02-06T03:14:37Z)
• Analyzing the Mechanism of Attention Collapse in VGGT from a Dynamics Perspective [13.434698786044107]
  Visual Geometry Grounded Transformer (VGGT) delivers state-of-the-art feed-forward 3D reconstruction.<n>Its global self-attention layer suffers from a drastic collapse phenomenon when the input sequence exceeds a few hundred frames.<n>We establish a rigorous mathematical explanation of the collapse by viewing the global-attention as a degenerate diffusion process.
  arXiv  Detail & Related papers  (2025-12-25T14:34:27Z)
• Towards Adversarial Robustness and Uncertainty Quantification in DINOv2-based Few-Shot Anomaly Detection [6.288045889067255]
  Foundation models such as DINOv2 have shown strong performance in few-shot anomaly detection.<n>We present one of the first systematic studies of adversarial attacks and uncertainty estimation in this setting.<n>We find that raw anomaly scores are poorly calibrated, revealing a gap between confidence and correctness that limits safety-critical use.
  arXiv  Detail & Related papers  (2025-10-15T15:06:45Z)
• Adaptive Dual Uncertainty Optimization: Boosting Monocular 3D Object Detection under Test-Time Shifts [80.32933059529135]
  Test-Time Adaptation (TTA) methods have emerged to adapt to target distributions during inference.<n>We propose Dual Uncertainty Optimization (DUO), the first TTA framework designed to jointly minimize both uncertainties for robust M3OD.<n>In parallel, we design a semantic-aware normal field constraint that preserves geometric coherence in regions with clear semantic cues.
  arXiv  Detail & Related papers  (2025-08-28T07:09:21Z)
• Neuro-Symbolic Entropy Regularization [78.16196949641079]
  In structured prediction, the goal is to jointly predict many output variables that together encode a structured object. One approach -- entropy regularization -- posits that decision boundaries should lie in low-probability regions. We propose a loss, neuro-symbolic entropy regularization, that encourages the model to confidently predict a valid object.
  arXiv  Detail & Related papers  (2022-01-25T06:23:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.