AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Contrastive Diffusion Guidance for Spatial Inverse Problems

Sattwik Basu, Chaitanya Amballa, Zhongweiyang Xu, Jorge Vančo Sampedro, Srihari Nelakuditi, Romit Roy Choudhury

ICLR 2026 · Image generation › Fast diffusion sampling · approach: Diffusion posterior sampling

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 intersection penalty (7e-4 vs 0) (ablation)CoGuide · HouseExpo, denseF1: 0.91 -> 0.95Improved
add intersection penalty (7e-4 vs 0) (ablation)CoGuide · HouseExpo, sparseIoU: 0.78 -> 0.84Improved
increase intersection weight from 7e-4 to 1.5e-3 (ablation)CoGuide · HouseExpo, denseF1: 0.95 -> 0.94Hurt
use Adam instead of GD in guidance step (ablation)CoGuide (DDIM) · HouseExpoF1: 0.86 -> 0.92Improved
use Adam instead of GD in guidance step (ablation)CoGuide (DDPM) · HouseExpoF1: 0.92 -> 0.94Improved
CoGuide instead of DPS with differentiable path plannersdiffusion inverse solver · HouseExpo, sparseF1: 0.79 -> 0.91Improved
CoGuide vs CFG at sparse trajectoriesfloorplan diffusion · HouseExpo, sparseF1: 0.86 -> 0.91Improved
CoGuide vs CFG at dense trajectoriesfloorplan diffusion · HouseExpo, denseF1: 0.97 -> 0.95Hurt
combine CFG prior with CoGuide guidanceCFG · HouseExpo, sparseF1: 0.86 -> 0.93Improved
increase measurement noise on trajectories (ablation)CoGuide · HouseExpoIoUHurt

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