AI Paper Atlas

Research map / 3D vision / Face and shape

Mitigating Perspective Distortion-induced Shape Ambiguity in Image Crops

Aditya Prakash, Arjun Gupta, Saurabh Gupta

ECCV 2024 · 3D vision › Face and shape · approach: Single-view 3D reconstruction · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add KPE (sparse) to ArcticNet-SFArcticNet-SF · ARCTIC egocentric (test)Success (%): 53.9 -> 64.1Improved
use object crops instead of full image (ablation)ArcticNet-SF · ARCTIC egocentric (validation)Success (%): 59.0 -> 66.0Improved
crop input without location info (ablation)ArcticNet-SF (crop) · ARCTIC egocentric (validation)CDev (mm): 44.1 -> 74.3Hurt
encode location in camera field of view with sinusoids (KPE) instead of 2D image location (ablation)ArcticNet-SF (crop) · ARCTIC egocentric (validation)Success (%): 67.9 -> 71.5Improved
encode both scale and location (corners and center) instead of center only (ablation)sparse KPE · ARCTIC egocentric (validation)Success (%): 66.8 -> 71.5Improved
feed dense KPE to the 7x7 feature map instead of the input (ablation)dense KPE · ARCTIC egocentric (validation)Success (%): 68.1 -> 71.4Improved
add dense KPE to ZoeDepth (no pretraining)ZoeD-X-N · NYU Depth v2REL: 0.093 -> 0.088Improved
add dense KPE to ZoeDepth (pretrained MiDaS)ZoeD-M12-N · NYU Depth v2REL: 0.088 -> 0.082Improved
add Cam-Conv to ZoeDepthZoeD-M12-N · NYU Depth v2REL: 0.088 -> 0.096Hurt
inject KPE inside the MiDaS backbone before BeiT instead of after (ablation)ZoeD-M12-N + KPE (dense) · NYU Depth v2REL: 0.085 -> 0.082Improved
add KPE (sparse) to Cube R-CNNCube R-CNN · KITTI + nuScenes Cars (joint)AP3D: 54.59 -> 57.54Improved
use sparse KPE instead of dense KPE for detection (ablation)Cube R-CNN + KPE · KITTI + nuScenes Cars (joint)AP3D: 56.78 -> 57.54Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy