cs.CVNov 3, 2026

ScoreDial: Precise Control of Visual Attributes in Image Generation via Regressor Guidance from Limited Human Ratings

Authors: Jianbo Tang, Keita Ishii, Hiroki Sakamoto, Manabu Kikuchi, Katsuma Kitamura, Chiho Semba, Kenta Nishiyama, Teppei Mori, 

Organizations: Keio University, Japan · Bridgestone Corporation, Japan

Abstract

Requested-value control is stricter than continuous steering: given cc on a human-rating scale, the generated image should attain that value from only limited ratings. We present ScoreDial, which fits a differentiable regressor RR to 100-479 human-rated images; once RR is fixed, a requested value cc is defined on its output scale, and learned target conditioning is paired with error-adaptive guidance that repeatedly reduces ∣R(x)−c∣|R(\mathbf{x})-c| during sampling. Across tire slip resistance, interior visual complexity, food desire-to-eat, and soap translucency, using one set of sampler settings, ScoreDial reaches requested values and achieves RR-MAE at most 0.013 over a range of width 0.8 and Spearman ρ=0.980ρ=0.980, the maximum attainable under our protocol. Because RR also drives sampling, we evaluate agreement with RR separately from matched sweeps, an independent auditor fitted to the same ratings on a backbone no deployed regressor uses, and blinded human judgments. MPGD-flow also reaches the requested values under RR, but ScoreDial has larger auditor displacement on every attribute, the largest among all compared methods, and a stronger MPGD-flow setting gives up target agreement without closing this gap. On every attribute, removing target conditioning leaves low RR-MAE but more than halves auditor displacement, separating precise score correction from attribute movement. Blinded rating studies with 15 raters per attribute show mean human ratings track cc on tire and soap, with linear R2=0.665R^2=0.665 and R2=0.786R^2=0.786, and in forced-choice comparisons of matched sweeps, raters chose ScoreDial's as the clearer progression in at least 84% of judgments against every baseline. Code: https://github.com/Kamijo-Gen/ScoreDial.

Figures & tables

Explore similar work

Sep 4, 2026

Measured Sliders: Learning Continuous Controls from Differentiable Image Measurements

Continuous sliders are useful only when coefficient changes produce predictable image changes. Yet most diffusion sliders derive their axes from text or learned representations, leaving their scales disconnected from observable image properties. Consequently, we cannot tell in advance which attributes are learnable, compare control strengths directly, or anticipate interference when multiple controls are combined. We propose Measured Sliders, a framework that defines continuous controls through closed-form differentiable image measurements. A common measurement space unifies the pipeline. Before training, an observability test identifies usable supervision. During training, a measurement-guided objective learns target movement while suppressing non-target changes. After training, decoded calibration expresses controls in comparable units of realized image change. Multiple LoRA branches are stored in one checkpoint and composed without training on joint activations. Across SDXL and FLUX.1-dev, the resulting controls are ordered, selective, and composable. On 553 prompts, lighting direction reaches rho = 0.995 and 98.9% monotone sweeps. A five-attribute checkpoint achieves average selectivity 2.59, compared with 1.50 for the strongest baseline, and preserves every requested direction in 96.7% of pair and 86.1% of triple compositions. The observability test also separates every subsequently successful measurement from the failed candidate. Overall, image-space measurement provides a common basis for learning, diagnosing, calibrating, and composing continuous generative controls.
Jun 8, 2026

Assessing Sample Quality in Conditional Generation under Compositional Shift

Conditional generators provide a natural tool for controllable generation, including settings where the desired condition is a new composition of observed attributes or experimental factors. In many applications, especially in scientific domains, such models are attractive to explore conditions for which real samples are rare, expensive, or not yet observed. However, this creates a circularity for evaluation: standard conditional quality metrics require a reference target distribution, but in the extrapolative regime that distribution is unavailable by definition. We address this problem with a post-hoc, per-sample trust score for assessing conditional samples using only the training distribution. The score combines two estimable quantities: global realism, measuring compatibility with the real data manifold, and attribute-wise faithfulness, measuring whether a sample is closer to the requested attributes than to plausible alternatives. We show that the score can recover meaningful comparisons across extrapolated generations, under a mild coverage condition on the observed attributes. These comparisons enable effective filtering, ranking, and abstention of generations and can be used directly on off-the-shelf pretrained models. In biological imaging, selected samples preserve real morphological structure better and improve downstream predictive performance, while similar gains are observed on controlled vision benchmarks. Finally, we show how the score can be applied during generation, enabling abstention before full decoding. Code is available at https://github.com/berkerdemirel/faithful-cond-gen.
Apr 13, 2026

RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time

Most reward models for visual generation reduce rich human judgments to a single unexplained score, discarding the reasoning that underlies preference. We show that teaching reward models to produce explicit, multi-dimensional critiques before scoring transforms them from passive evaluators into active optimization tools, improving generators in two complementary ways: at training time, structured rationales provide interpretable, fine-grained rewards for reinforcement learning; at test time, a Generate-Critique-Refine loop turns critiques into targeted prompt revisions that improve outputs without any parameter updates. To train such a reward model without costly rationale annotations, we introduce Preference-Anchored Rationalization (PARROT), a principled framework that recovers high-quality rationales from readily available preference data through anchored generation, consistency filtering, and distillation. The resulting model, RationalRewards (8B), achieves state-of-the-art preference prediction among open-source reward models, competitive with Gemini-2.5-Pro, while using 10-20x less training data than comparable baselines. As an RL reward, it consistently improves text-to-image and image-editing generators beyond scalar alternatives. Most strikingly, its test-time critique-and-refine loop matches or exceeds RL-based fine-tuning on several benchmarks, suggesting that structured reasoning can unlock latent capabilities in existing generators that suboptimal prompts fail to elicit.