AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

JointDiT: Enhancing RGB-Depth Joint Modeling with Diffusion Transformers

Kwon Byung-Ki, Qi Dai, Lee Hyoseok, Chong Luo, Tae-Hyun Oh

ICCV 2025 · Image generation › Fast diffusion sampling · approach: Distributional control of diffusion · 10 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 adaptive scheduling weights (ablation)JointDiT · ImageNet 6K joint generationFID: 30.88 -> 24.20Improved
add adaptive scheduling weights (ablation)JointDiT · MSCOCO 30K joint generationFID: 15.17 -> 11.13Improved
add adaptive scheduling weights (ablation)JointDiT · NYUv2 depth estimationAbsRel: 8.8 -> 6.4Improved
add unbalanced timestep sampling (ablation)JointDiT · NYUv2 depth estimationAbsRel: 8.8 -> 7.8Improved
add unbalanced timestep sampling on top of adaptive weights (ablation)JointDiT · NYUv2 depth estimationAbsRel: 6.4 -> 5.7Improved
add unbalanced timestep sampling without adaptive weights (ablation)JointDiT · ImageNet 6K joint generationFID: 30.88 -> 29.37Improved
add unbalanced timestep sampling on top of adaptive weights (ablation)JointDiT · ImageNet 6K joint generationFID: 24.20 -> 24.26No clear effect
add unbalanced timestep sampling on top of adaptive weights (ablation)JointDiT · ImageNet 6K joint generationIS: 37.04 -> 37.81Improved
add adaptive scheduling weights (ablation)JointDiT · OpenImages 6K depth-conditioned generationFID: 11.94 -> 14.37Hurt
add unbalanced timestep sampling on top of adaptive weights (ablation)JointDiT · OpenImages 6K depth-conditioned generationFID: 14.37 -> 12.58Improved
add both adaptive weights and unbalanced timestep (ablation)JointDiT · OpenImages 6K depth-conditioned generationImageReward Rank1: 26.35 -> 30.73Improved
increase LoRA rank from 16 to 64 (ablation)JointDiT · NYUv2 depth estimationAbsRel: 9.1 -> 5.7Improved

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