VLMs across families and scales show anchoring to discrete slant angles in zero-shot and prompted settings rather than human-like graded texture-based slant perception.
Advances in neural information processing systems27 (2014)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
Sphere-Depth benchmark shows substantial performance degradation in both general and spherical-aware depth estimation models under simulated camera pose variations.
FoundDP integrates DP-derived metric depth with ViT-based structural priors from monocular models, using feature alignment to mitigate defocus blur and improve depth in low-observability areas.
citing papers explorer
-
Anchored, Not Graded: Vision-Language Models Fail at Slant-from-Texture Perception
VLMs across families and scales show anchoring to discrete slant angles in zero-shot and prompted settings rather than human-like graded texture-based slant perception.
-
Sphere-Depth: A Benchmark for Depth Estimation Methods with Varying Spherical Camera Orientations
Sphere-Depth benchmark shows substantial performance degradation in both general and spherical-aware depth estimation models under simulated camera pose variations.
-
FoundDP: Revisiting Weak Disparity Observability in Dual-Pixel Depth Estimation
FoundDP integrates DP-derived metric depth with ViT-based structural priors from monocular models, using feature alignment to mitigate defocus blur and improve depth in low-observability areas.