While virtual try-on for clothes and shoes with diffusion models has gained attraction, virtual try-on for ornaments, such as bracelets, rings, earrings, and necklaces, remains largely unexplored. Due to the intricate tiny patterns and repeated geometric sub-structures in most ornaments, it is much more difficult to guarantee identity and appearance consistency under large pose and scale variances between ornaments and models. This paper proposes the task of virtual try-on for ornaments and presents a method to improve the geometric and appearance preservation of ornament virtual try-ons. Specifically, we estimate an accurate wearing mask to improve the alignments between ornaments and models in an iterative scheme alongside the denoising process. To preserve structure details, we further regularize attention layers to map the reference ornament mask to the wearing mask in an implicit way. Experimental results demonstrate that our method successfully wears ornaments from reference images onto target models, handling substantial differences in scale and pose while preserving identity and achieving realistic visual effects.

To generate 3D objects, early research focused on multi-view-driven approaches relying solely on 2D renderings. Recently, the 3D native latent diffusion paradigm has demonstrated superior performance in 3D generation, because it fully leverages the geometric information provided in ground truth 3D data. Despite its fast development, 3D diffusion still faces three challenges. First, the majority of these methods represent a 3D object by one single latent, regardless of its complexity. This may lead to detail loss when generating 3D objects with multiple complicated parts. Second, most 3D assets are designed parts by parts, yet the current holistic latent representation overlooks the independence of these parts and their interrelationships, limiting the model's generative ability. Third, current methods rely on global conditions (e.g., text, image, point cloud) to control the generation process, lacking detailed controllability. Therefore, motivated by how 3D designers create a 3D object, we present a new part-based 3D generation framework, CoPart, which represents a 3D object with multiple contextual part latents and simultaneously generates coherent 3D parts. This part-based framework has several advantages, including: i) reduces the encoding burden of intricate objects by decomposing them into simpler parts, ii) facilitates part learning and part relationship modeling, and iii) naturally supports part-level control. Furthermore, to ensure the coherence of part latents and to harness the powerful priors from foundation models, we propose a novel mutual guidance strategy to fine-tune pre-trained diffusion models for joint part latent denoising. Benefiting from the part-based representation, we demonstrate that CoPart can support various applications including part-editing, articulated object generation, and mini-scene generation. Moreover, we collect a new large-scale 3D part dataset named Partverse from Objaverse through automatic mesh segmentation and subsequent human post-annotations. By training on the proposed dataset, CoPart achieves promising part-based 3D generation with high controllability. Project page: https://hkdsc.github.io/project/copart.

Inserting 3D objects into videos is a longstanding challenge in computer graphics with applications in augmented reality, virtual try-on, and video composition. Achieving both temporal consistency, or realistic lighting remains difficult, particularly in dynamic scenarios with complex object motion, perspective changes, and varying illumination. While 2D diffusion models have shown promise for producing photorealistic edits, they often struggle with maintaining temporal coherence across frames. Conversely, traditional 3D rendering methods excel in spatial and temporal consistency but fall short in achieving photorealistic lighting. In this work, we propose a hybrid object insertion pipeline that combines the strengths of both paradigms. Specifically, we focus on inserting bracelets into dynamic wrist scenes, leveraging the high temporal consistency of 3D Gaussian Splatting (3DGS) for initial rendering and refining the results using a 2D diffusion-based enhancement model to ensure realistic lighting interactions. Our method introduces a shading-driven pipeline that separates intrinsic object properties (albedo, shading, reflectance) and refines both shading and sRGB images for photorealism. To maintain temporal coherence, we optimize the 3DGS model with multi-frame weighted adjustments. This is the first approach to synergize 3D rendering and 2D diffusion for video object insertion, offering a robust solution for realistic and consistent video editing. Project Page: https://cjeen.github.io/BraceletPaper/

Most 3D generation research focuses on up-projecting 2D foundation models into the 3D space, either by minimizing 2D Score Distillation Sampling (SDS) loss or fine-tuning on multi-view datasets. Without explicit 3D priors, these methods often lead to geometric anomalies and multi-view inconsistency. Recently, researchers have attempted to improve the genuineness of 3D objects by directly training on 3D datasets, albeit at the cost of low-quality texture generation due to the limited texture diversity in 3D datasets. To harness the advantages of both approaches, we propose Bidirectional Diffusion (BiDiff), a unified framework that incorporates both a 3D and a 2D diffusion process, to preserve both 3D fidelity and 2D texture richness, respectively. Moreover, as a simple combination may yield inconsistent generation results, we further bridge them with novel bidirectional guidance. In addition, our method can be used as an initialization of optimization-based models to further improve the quality of 3D models and the efficiency of optimization, reducing the process from 3.4 hours to 20 minutes. Experimental results have shown that our model achieves high-quality, diverse, and scalable 3D generation. Project website https://bidiff.github.io/.

3D object generation has undergone significant advancements, yielding high-quality results. However, fall short of achieving precise user control, often yielding results that do not align with user expectations, thus limiting their applicability. User-envisioning 3D object generation faces significant challenges in realizing its concepts using current generative models due to limited interaction capabilities. Existing methods mainly offer two approaches: (i) interpreting textual instructions with constrained controllability, or (ii) reconstructing 3D objects from 2D images. Both of them limit customization to the confines of the 2D reference and potentially introduce undesirable artifacts during the 3D lifting process, restricting the scope for direct and versatile 3D modifications. In this work, we introduce Interactive3D, an innovative framework for interactive 3D generation that grants users precise control over the generative process through extensive 3D interaction capabilities. Interactive3D is constructed in two cascading stages, utilizing distinct 3D representations. The first stage employs Gaussian Splatting for direct user interaction, allowing modifications and guidance of the generative direction at any intermediate step through (i) Adding and Removing components, (ii) Deformable and Rigid Dragging, (iii) Geometric Transformations, and (iv) Semantic Editing. Subsequently, the Gaussian splats are transformed into InstantNGP. We introduce a novel (v) Interactive Hash Refinement module to further add details and extract the geometry in the second stage. Our experiments demonstrate that proposed Interactive3D markedly improves the controllability and quality of 3D generation. Our project webpage is available at https://interactive-3d.github.io/.

Visual-inertial SLAM (VI-SLAM) is a key technology for Augmented Reality (AR), which allows the AR device to recover its 6-DoF motion in real-time in order to render the virtual content with the corresponding pose. Nowadays, smartphones are still the mainstream devices for ordinary users to experience AR. However the current VI-SLAM methods, although performing well on high-end phones, still face robustness challenges when deployed on a larger stock of mid- and low-end phones. Existing VI-SLAM datasets use either very ideal sensors or only a limited number of devices for data collection, which cannot reflect the capability gaps that VI-SLAM methods need to solve when deployed on a large variety of phone models. This work proposes 100-Phones. the first VI-SLAM dataset covering a wide range of mainstream phones in the market. The dataset consists of 350 sequences collected by 100 different models of phones. Through analysis and experiments on the collected data, we conclude that the quality of visual-inertial data vary greatly among the mainstream phones, and the current open source VI-SLAM methods still have serious robustness issues when it comes to mass deployment on mobile phones. We release the dataset to facilitate the robustness improvement of VI-SLAM and to promote the mass popularization of AR. Project page: https://github.com/zju3dv/100-Phones.

Animation plays an important role in virtual reality and augmented reality applications. However, it requires great efforts for non-professional users to create animation assets. In this paper, we propose a systematic pipeline to generate ready-to-used characters from images for real-time animation without user intervention. Rather than per-pixel mapping or synthesis in image space using optical flow or generative models, we employ an approximate geometric embodiment to undertake 3D animation without large distortion. The geometry structure is generated from a type-agnostic character. A skeleton adaption is then adopted to guarantee semantic motion transfer to the geometry proxy. The generated character is compatible with standard 3D graphics engines and ready to use for real-time applications. Experiments show that our method works on various images (e.g. sketches, cartoons, and photos) of most object categories (e.g. human, animals, and non-creatures). We develop an AR demo to show its potential usage for fast prototyping.

We study the problem of resource-efficient uplink distribution of user-generated video content over fourth-generation mobile networks. This is challenged by (1) the capacity-limited and time-variant uplink channel, (2) the resource-hungry upstreamed videos and their dynamically changing complexity, and (3) the different playout times of the video consumers. To address these issues, we propose a systematic approach for quality-of-experience (QoE)-based resource optimization and uplink transmission of multiuser generated video content. More specifically, we present an analytical model for distributed scalable video transmission at the mobile producers which considers these constraints. This is complemented by a multiuser cross-layer optimizer in the mobile network which determines the transmission capacity for each mobile terminal under current cell load and radio conditions. Both optimal and low-complexity solutions are presented. Simulation results for LTE uplink transmission show that significant gains in perceived video quality can be achieved by our cross-layer resource optimization scheme. In addition, the distributed optimization at the mobile producers can further improve the user experience across the different types of video consumers.

We address how human pose in 3D can be tracked from a monocular video using a probabilistic inference method. Human body is modeled as a number of cylinders in space, each with an appearance facet as well as a pose facet. The appearance facets are acquired in a learning phase from some beginning frames of the input video. On this the visual hull description of the target human subject constructed from multiple images is found to be instrumental. In the operation phase, the 3D pose of the target subject in the subsequent frames of the input video is tracked. A bottom-up framework is used, which for any current image frame extracts firstly the tentative candidates of each body part in the image space. The human model, with the appearance facets already learned, and with the pose entries initialized with those for the previous image frame, is then brought in under a belief propagation algorithm, to establish correlation with the above 2D body part candidates while enforcing the proper articulation between the body parts, thereby determining the 3D pose of the human body in the current frame. The tracking performance on a number of monocular videos is shown.