Photo exposure correction is widely investigated, but fewer studies focus on correcting under- and over-exposed images simultaneously. Three issues remain open to handle and correct both under- and over-exposed images in a unified way. First, a locally adaptive exposure adjustment may be more flexible instead of learning a global mapping. Second, it is an ill-posed problem to determine the suitable exposure values locally. Third, photos with the same content but different exposures may not reach consistent adjustment results. To this end, we proposed a novel exposure correction network, ExReg, to address the challenges by formulating exposure correction as a multi-dimensional regression process. Given an input image, a compact multi-exposure generation network is introduced to generate images with different exposure conditions for multi-dimensional regression and exposure correction in the next stage. An auxiliary module is designed to predict the region-wise exposure values, guiding the proposed Encoder–Decoder ANP (Attentive Neural Process) to regress the final corrected image. The experimental results show that ExReg can generate well-exposed results and outperform the SOTA method in PSNR for extensive exposure problems. Furthermore, the processing speed, with 0.05 seconds per image on an RTX 3090, is efficient. When tested on the same image under various exposure levels, ExReg also yields results that are visually consistent and physically accurate.

Blind Face Restoration aims to recover high-fidelity, detail-rich facial images from unknown degraded inputs, presenting significant challenges in preserving both identity and detail. Pre-trained diffusion models have been increasingly used as image priors to generate fine details. Still, existing methods often use fixed diffusion sampling timesteps and a global guidance scale, assuming uniform degradation. This limitation and potentially imperfect degradation kernel estimation frequently lead to under- or over-diffusion, resulting in an imbalance between fidelity and quality. We propose DynFaceRestore, a novel blind face restoration approach that learns to map any blindly degraded input to Gaussian blurry images. By leveraging these blurry images and their respective Gaussian kernels, we dynamically select the starting timesteps for each blurry image and apply closed-form guidance during the diffusion sampling process to maintain fidelity. Additionally, we introduce a dynamic guidance scaling adjuster that modulates the guidance strength across local regions, enhancing detail generation in complex areas while preserving structural fidelity in contours. This strategy effectively balances the trade-off between fidelity and quality. DynFaceRestore achieves state-of-the-art performance in both quantitative and qualitative evaluations, demonstrating robustness and effectiveness in blind face restoration. Project page at https://nycu-acm.github.io/DynFaceRestore/

Face recognition (FR) has achieved unprecedented success in high-resolution face recognition (HRFR) scenarios. However, applying the models trained on HRFR tasks to cross-resolution face recognition (CRFR) or low-resolution face recognition (LRFR) results in performance decline. This is attributed to the challenges in extracting identity-preserving features from low-resolution images. To address this, we present Lipface, an FR model fortified with Lipschitz constraints, designed to perform robustly across varying face resolutions. Also, recognizing the differential impact of training images based on their quality, we adopt the feature norm as an image quality metric. This allows our model to weigh the significance of samples during training dynamically. Experiments demonstrate that, under various backbones and training datasets, Lipface outperforms state-of-the-art FR methods. Across two HRFR datasets (LFW and IJBB), one LRFR dataset (Tinyface), and two CRFR datasets (SCface and XQLFW), Lipface achieves an average improvement ranging from 1.92% to 6.07% across the five datasets.

We present TimeNeRF, a generalizable neural rendering approach for rendering novel views at arbitrary viewpoints and at arbitrary times, even with few input views. For real-world applications, it is expensive to collect multiple views and inefficient to re-optimize for unseen scenes. Moreover, as the digital realm, particularly the metaverse, strives for increasingly immersive experiences, the ability to model 3D environments that naturally transition between day and night becomes paramount. While current techniques based on Neural Radiance Fields (NeRF) have shown remarkable proficiency in synthesizing novel views, the exploration of NeRF's potential for temporal 3D scene modeling remains limited, with no dedicated datasets available for this purpose. To this end, our approach harnesses the strengths of multi-view stereo, neural radiance fields, and disentanglement strategies across diverse datasets. This equips our model with the capability for generalizability in a few-shot setting, allows us to construct an implicit content radiance field for scene representation, and further enables the building of neural radiance fields at any arbitrary time. Finally, we synthesize novel views of that time via volume rendering. Experiments show that TimeNeRF can render novel views in a few-shot setting without per-scene optimization. Most notably, it excels in creating realistic novel views that transition smoothly across different times, adeptly capturing intricate natural scene changes from dawn to dusk.

Abstract Rescaling digital images for display on various devices, while simultaneously removing noise, has increasingly become a focus of attention. However, limited research has been done on a unified framework that can efficiently perform both tasks. In response, we propose INDIRECT (INvertible and Discrete noisy Image Rescaling with Enhancement from Case-dependent Textures), a novel method designed to address image denoising and rescaling jointly. INDIRECT leverages a jointly optimized framework to produce clean and visually appealing images using a lightweight model. It employs a discrete invertible network, DDR-Net, to perform rescaling and denoising through its reversible operations, efficiently mitigating the quantization errors typically encountered during downscaling. Subsequently, the Case-dependent Texture Module (CTM) is introduced to estimate missing high-frequency information, thereby recovering a clean and high-resolution image. Experimental results demonstrate that our method achieves competitive performance across three tasks: noisy image rescaling, image rescaling, and denoising, all while maintaining a relatively small model size.