相关论文: MatE: Material Extraction from Single-Image via Ge…

Human matting is a foundation task in image and video processing, where human foreground pixels are extracted from the input. Prior works either improve the accuracy by additional guidance or improve the temporal consistency of a single…

In recent years, the underwater image formation model has found extensive use in the generation of synthetic underwater data. Although many approaches focus on scenes primarily affected by discoloration, they often overlook the model's…

In the portrait matting, the goal is to predict an alpha matte that identifies the effect of each pixel on the foreground subject. Traditional approaches and most of the existing works utilized an additional input, e.g., trimap, background…

There has been significant progress in Masked Image Modeling (MIM). Existing MIM methods can be broadly categorized into two groups based on the reconstruction target: pixel-based and tokenizer-based approaches. The former offers a simpler…

High-quality material generation is key for virtual environment authoring and inverse rendering. We propose MaterialPicker, a multi-modal material generator leveraging a Diffusion Transformer (DiT) architecture, improving and simplifying…

The reconstruction of indoor scenes from multi-view RGB images is challenging due to the coexistence of flat and texture-less regions alongside delicate and fine-grained regions. Recent methods leverage neural radiance fields aided by…

Text-to-3D generation by distilling pretrained large-scale text-to-image diffusion models has shown great promise but still suffers from inconsistent 3D geometric structures (Janus problems) and severe artifacts. The aforementioned problems…

Despite remarkable advancements in video depth estimation, existing methods exhibit inherent limitations in achieving geometric fidelity through the affine-invariant predictions, limiting their applicability in reconstruction and other…

Image matting is a long-standing problem in computer graphics and vision, mostly identified as the accurate estimation of the foreground in input images. We argue that the foreground objects can be represented by different-level…

Video diffusion models have recently enabled high-quality video generation with ViT-based architectures, but remain computationally intensive because generation requires attention computation over long spatiotemporal sequences. Token…

We propose DiMeR, a novel geometry-texture disentangled feed-forward model with 3D supervision for sparse-view mesh reconstruction. Existing methods confront two persistent obstacles: (i) textures can conceal geometric errors, i.e.,…

Variational Autoencoders (VAE) are probabilistic deep generative models underpinned by elegant theory, stable training processes, and meaningful manifold representations. However, they produce blurry images due to a lack of explicit…

Image matting aims to obtain an alpha matte that separates foreground objects from the background accurately. Recently, trimap-free matting has been well studied because it requires only the original image without any extra input. Such…

Inferring full-body poses from Head Mounted Devices, which capture only 3-joint observations from the head and wrists, is a challenging task with wide AR/VR applications. Previous attempts focus on learning one-stage motion mapping and thus…

Reconstructing object geometry and material from multiple views typically requires optimization. Differentiable path tracing is an appealing framework as it can reproduce complex appearance effects. However, it is difficult to use due to…

We present PIXLRelight, a feed-forward approach for physically controllable single-image relighting. Existing methods either provide limited lighting control (e.g. through text or environment maps), accumulate errors when chaining inverse…

We present a novel approach to leverage prior knowledge encapsulated in pre-trained text-to-image diffusion models for blind super-resolution (SR). Specifically, by employing our time-aware encoder, we can achieve promising restoration…

Real-world image super-resolution (RealSR) aims to enhance the visual quality of in-the-wild images, such as those captured by mobile phones. While existing methods leveraging large generative models demonstrate impressive results, the high…

This paper proposes a deep learning based method for colored transparent object matting from a single image. Existing approaches for transparent object matting often require multiple images and long processing times, which greatly hinder…

We introduce an inversion based method, denoted as IMAge-Guided model INvErsion (IMAGINE), to generate high-quality and diverse images from only a single training sample. We leverage the knowledge of image semantics from a pre-trained…