Signals 4 · free daily AI digest

Pumpire: Unified Benchmark for Metric Distance Estimation

Paper recorded by Signals 4 on 2026-10-08 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-08 on arXiv · recorded by Signals 4 on 2026-10-09

Category: cs.CV · 计算机视觉 · first seen 2026-10-09

Abstract

We present Pumpire, a unified benchmark for evaluating metric point-pair distance estimation capability of both image- and video-level 3D foundation models, with or without depth priors. In contrast to previous approaches that normally evaluate depth and camera intrinsics separately or evaluate point-clouds with geometric similarity metrics, which cannot directly reflect models' point-to-point dis

Read on arXiv →

#314 most recent of 756 cs.CV papers we have recorded · ↑ newer: LEGO: A Lifting-Free Approach for Exocentric-to-Egocentric Video Gener · ↓ older: OneSearch-VL: Unified Multimodal Deep Research Agent for Image and Vid
Cite this page: Pumpire: Unified Benchmark for Metric Distance Estimation: the #314 most recent of 756 cs.CV papers we have recorded (as of 2026-10-08). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/pumpire-unified-benchmark-for-metric-distance-estimation.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CV papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions