#depth estimation

try —

5 papers match

cs.CV2026

Explainable and Resource-Efficient Spatial Reasoning in Multimodal LLMs for Decision-Critical Applications

Piyush Jain, Kousik Dasgupta, Rajarshi Roy +1

The paper introduces ByDeWay-V2, a training‑free prompting framework that adds explicit pairwise spatial predicates derived from depth estimation and open‑vocabulary object detecti…

#multimodal large language models#spatial reasoning#depth estimation#prompt engineering
cs.CV2026

X-Lens: Real-Time Metric Depth Estimation with Heterogeneous Cameras

Heng Zhou, Shuhong Liu, Yonghao He +6

X-Lens is a compact feed‑forward model that estimates metric depth in real time from a mix of calibrated fisheye and pinhole camera views using geometry‑aware calibration tokens an…

#depth estimation#heterogeneous cameras#real-time perception#fisheye
cs.CV2026

GeCo: Evaluating Geometric Consistency for Video Generation via Motion and Structure

Leslie Gu, Junhwa Hur, Charles Herrmann +4

GeCo is a geometry-based metric that detects deformation and occlusion inconsistencies in generated videos by combining residual motion and depth cues, providing dense consistency…

#video generation#geometric consistency#motion analysis#depth estimation
cs.CV2026

GHOST: Geometry-Guided Hallucination of Opaque Surface Textures

Langxu Zhao, Zuan Gu, Tianhan Gao

The paper introduces GHOST, a preprocessing framework that converts transparent regions into opaque, texture-rich images using geometry-guided hallucination, improving depth estima…

#transparent objects#depth estimation#3d reconstruction#texture synthesis
cs.CV2026

When Depth Is Better Told Than Shown: Depth-Ordinal Prompting for Vision-Language Spatial Reasoning

Quynh Vo, Phuc Dao, Cong-Duy Nguyen +1

The paper introduces Depth-Ordinal Prompting (DOP), a training‑free technique that converts monocular depth estimates into object‑level ordinal text cues, enabling vision‑language…

#spatial reasoning#depth estimation#vision-language models#prompt engineering

One search, two signals: results blend meaning (embedding similarity, so papers that never use your words still surface) with keyword matches on titles, abstracts and summaries. Free, no sign-in needed.