Nima Kalantari

Xilong Zhou, Bao-Huy Nguyen, Zheng Zeng et al.

Video generative models have achieved remarkable progress in synthesizing photorealistic video sequences. However, enabling broader and more creative downstream applications requires fine-grained instance-level video editing, including object insertion, object removal, and texture editing, which has emerged as a prominent yet challenging problem. Existing approaches either propose unified generative frameworks with only coarse semantic control, or design task-specific frameworks for individual editing tasks, limiting their flexibility and applicability across diverse real-world scenarios. To address these limitations, we propose AlbedoEdit, a unified generative video editing framework that jointly supports object insertion, object removal, and texture editing. Our key insight is that the intrinsic albedo map, which is invariant to lighting and contains no specularity, shadowing and inter-reflection effects, provides an effective and user-friendly mechanism for specifying fine-grained appearance edits. Built upon video foundation models, AlbedoEdit is fine-tuned to translate source RGB videos into edited RGB videos, conditioned on a user-edited first-frame albedo. Trained on a new paired synthetic dataset covering all three editing tasks, AlbedoEdit implicitly learns to harmonize edited contents and simulate complex real-world visual effects triggered by editing operations, including specular highlights, soft shadows, and mirror reflections. AlbedoEdit demonstrates superior performance over state-of-the-art video editing approaches, both qualitatively and quantitatively. Project webpage is https://vcai.mpi-inf.mpg.de/projects/AlbedoEdit/.

Xilong Zhou, Miloš Hašan, Valentin Deschaintre et al.

Recent methods (e.g. MaterialGAN) have used unconditional GANs to generate per-pixel material maps, or as a prior to reconstruct materials from input photographs. These models can generate varied random material appearance, but do not have any mechanism to constrain the generated material to a specific category or to control the coarse structure of the generated material, such as the exact brick layout on a brick wall. Furthermore, materials reconstructed from a single input photo commonly have artifacts and are generally not tileable, which limits their use in practical content creation pipelines. We propose TileGen, a generative model for SVBRDFs that is specific to a material category, always tileable, and optionally conditional on a provided input structure pattern. TileGen is a variant of StyleGAN whose architecture is modified to always produce tileable (periodic) material maps. In addition to the standard "style" latent code, TileGen can optionally take a condition image, giving a user direct control over the dominant spatial (and optionally color) features of the material. For example, in brick materials, the user can specify a brick layout and the brick color, or in leather materials, the locations of wrinkles and folds. Our inverse rendering approach can find a material perceptually matching a single target photograph by optimization. This reconstruction can also be conditional on a user-provided pattern. The resulting materials are tileable, can be larger than the target image, and are editable by varying the condition.

Libing Zeng, Lele Chen, Yi Xu et al.

In this paper, we propose an approach to obtain a personalized generative prior with explicit control over a set of attributes. We build upon MyStyle, a recently introduced method, that tunes the weights of a pre-trained StyleGAN face generator on a few images of an individual. This system allows synthesizing, editing, and enhancing images of the target individual with high fidelity to their facial features. However, MyStyle does not demonstrate precise control over the attributes of the generated images. We propose to address this problem through a novel optimization system that organizes the latent space in addition to tuning the generator. Our key contribution is to formulate a loss that arranges the latent codes, corresponding to the input images, along a set of specific directions according to their attributes. We demonstrate that our approach, dubbed MyStyle++, is able to synthesize, edit, and enhance images of an individual with great control over the attributes, while preserving the unique facial characteristics of that individual.

Mohammad Reza Karimi Dastjerdi, Dominique Tanguay-Gaudreau, Frédéric Fortier-Chouinard et al.

Most novel view synthesis methods-including Neural Radiance Fields (NeRF)-struggle to capture the true high dynamic range (HDR) radiance of scenes. This is primarily due to their dependence on low dynamic range (LDR) images from conventional cameras. Exposure bracketing techniques aim to address this challenge, but they introduce a considerable time burden during the acquisition process. In this work, we introduce PanDORA: PANoramic Dual-Observer Radiance Acquisition, a system designed for the casual, high quality HDR capture of indoor environments. Our approach uses two 360° cameras mounted on a portable monopod to simultaneously record two panoramic 360° videos: one with standard exposure and another at fast shutter speed. The resulting video data is processed by a proposed two-stage NeRF-based algorithm, including an algorithm for the fine alignment of the fast- and well-exposed frames, generating non-saturated HDR radiance maps. Compared to existing methods on a novel dataset of real indoor scenes captured with our apparatus and including HDR ground truth lighting, PanDORA achieves superior visual fidelity and provides a scalable solution for capturing real environments in HDR.

Andrii Litvynchuk, Ivan Livinsky, Anand Ravi et al.

Monocular depth estimation (MDE) plays a pivotal role in various computer vision applications, such as robotics, augmented reality, and autonomous driving. Despite recent advancements, existing methods often fail to meet key requirements for 3D reconstruction and view synthesis, including geometric consistency, fine details, robustness to real-world challenges like reflective surfaces, and efficiency for edge devices. To address these challenges, we introduce a novel MDE system, called EfficientDepth, which combines a transformer architecture with a lightweight convolutional decoder, as well as a bimodal density head that allows the network to estimate detailed depth maps. We train our model on a combination of labeled synthetic and real images, as well as pseudo-labeled real images, generated using a high-performing MDE method. Furthermore, we employ a multi-stage optimization strategy to improve training efficiency and produce models that emphasize geometric consistency and fine detail. Finally, in addition to commonly used objectives, we introduce a loss function based on LPIPS to encourage the network to produce detailed depth maps. Experimental results demonstrate that EfficientDepth achieves performance comparable to or better than existing state-of-the-art models, with significantly reduced computational resources.