AI Paper Atlas

Research map / 3D vision / Face and shape

Novel Views of Objects from a Single Image

Konstantinos Rematas, Chuong H. Nguyen, Tobias Ritschel, Mario Fritz, Tinne Tuytelaars

TPAMI 2016 · 3D vision › Face and shape · approach: Single-view 3D reconstruction

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 synthesized novel views to 26 side-view training imagesDPM, side views · PASCAL VOC 2007 car testaverage precision (%): 16.2 -> 30.2 (N=3)Improved
add synthesized novel views to full VOC training setDPM, full VOC · PASCAL VOC 2007 car testaverage precision (%): 51.7 -> 50.2 (N=3)No clear effect
add synthesized novel views to full VOC training setDPM, full VOC · PASCAL VOC 2007 car test (rare viewpoints)average precision (%): 53.1 vs 52.5 -> 57.3 (N=4)Improved
add synthesized novel views to side viewsDPM, side views · PASCAL VOC 2007 car test (rare viewpoints)average precision (%): 10.3 -> 32.9 (N=5)Improved
add synthesized novel views to side viewsDPM, side views · UCLA cars testaverage precision (%): 41.5 -> 83.0 (N=3)Improved
add synthesized novel views to full VOC training setDPM, full VOC · UCLA cars testaverage precision (%): 75.4 -> 84.0 (N=3)Improved
add synthesized novel views to full VOC training setDPM, full VOC · UCLA cars test (rare viewpoints)average precision (%): 69.8 -> 81.4 (N=3)Improved
use rendered 3D model instead of real car in trainingDPM · PASCAL VOC 2007 car (pilot)average precision (%): 15.4 -> 11.5 (N=1)Hurt
use re-synthesized car instead of real car in trainingDPM · PASCAL VOC 2007 car (pilot)average precision (%): 15.4 -> 15.0 (N=1)No clear effect
add fine alignment stage with on-the-fly rendering to coarse alignment (ablation)2D-to-3D alignment · Pascal3D subset (80 images)alignment performance ratio to reference: 5% average improvement, roughly 5 times fasterImproved
use final coarse sampling scheme (mask, view, envmap, roll variation) over exemplar (ablation)2D-to-3D alignment · Pascal3D subset (80 images)alignment performance ratio to reference: 2-3% improvement, approx 40 fold speedupImproved
add pruning by user mask bounding box (ablation)coarse alignment · per-class samplessamples tested: 633 out of 6400 samples testedImproved

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