AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Camera Control for Text-to-Image Generation via Learning Viewpoint Tokens

Xinxuan Lu, Charless Fowlkes, Alexander C. Berg

CVPR 2026 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 1 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
use factorized viewpoint encoding instead of Plucker rays (ablation)Ours (Harmon) · Viewpoint test set (5,550 samples)azimuth mean error (deg): 21.61 -> 18.11Improved
use factorized encoding instead of 12D camera matrix (ablation)Ours (Harmon) · Viewpoint test set (5,550 samples)azimuth mean error (deg): 24.44 -> 18.11Improved
use factorized encoding instead of sinusoidal encoding (ablation)Ours (Harmon) · Viewpoint test set (5,550 samples)azimuth mean error (deg): 60.90 -> 18.11Improved
add the rendered 3D subset to the training data (ablation)Ours (Harmon) · Viewpoint test set (5,550 samples)azimuth mean error (deg): 22.98 -> 18.11Improved
fine-tune the backbone instead of freezing it (ablation)Ours (Harmon) · Viewpoint test set (5,550 samples)azimuth mean error (deg): 40.19 -> 18.11Improved
add additional viewpoint tokens (ablation)Ours (Harmon) · Viewpoint test set (5,550 samples)azimuth mean error (deg): 18.11 -> 18.03No clear effect
swap Harmon backbone for SD3.5 (ablation)Ours · Viewpoint test set (5,550 samples)azimuth mean error (deg): 18.11 -> 12.85Mixed
swap Harmon backbone for SD2.1 (ablation)Ours · Viewpoint test set (5,550 samples)azimuth mean error (deg): 18.11 -> 19.16No clear effect
use global-context viewpoint tokens (ours) instead of Compass ControlCompass Control · Viewpoint test set (5,550 samples)azimuth mean error (deg): 31.07 -> 18.11Improved
use ours instead of Compass Control on diverse objectsCompass Control · Diverse set (26 objects)azimuth mean error (deg): 37.29 -> 19.06Improved
use ours instead of Compass Control on GenEval colorsCompass Control · GenEvalGenEval colors: 58.78 -> 76.60Improved
fine-tune Harmon with viewpoint tokensHarmon · GenEvalGenEval single object: 99.90 -> 94.38Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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