Birth and Death of a Rose

We study the problem of generating temporal object intrinsics -- temporally evolving sequences of object geometry, reflectance, and texture, such as a blooming rose -- from pre-trained 2D foundation models. Unlike conventional 3D modeling and animation techniques that require extensive manual effort and expertise, we introduce a method that generates such assets with signals distilled from pre-trained 2D diffusion models. To ensure the temporal consistency of object intrinsics, we propose Neural Templates for temporal-state-guided distillation, derived automatically from image features from self-supervised learning. Our method can generate high-quality temporal object intrinsics for several natural phenomena and enable the sampling and controllable rendering of these dynamic objects from any viewpoint, under any environmental lighting conditions, at any time of their lifespan. Project website: https://chen-geng.com/rose4d

ShapeCraft: Body-Aware and Semantics-Aware 3D Object Design

For designing a wide range of everyday objects, the design process should be aware of both the human body and the underlying semantics of the design specification. However, these two objectives present significant challenges to the current AI-based designing tools. In this work, we present a method to synthesize body-aware 3D objects from a base mesh given an input body geometry and either text or image as guidance. The generated objects can be simulated on virtual characters, or fabricated for real-world use. We propose to use a mesh deformation procedure that optimizes for both semantic alignment as well as contact and penetration losses. Using our method, users can generate both virtual or real-world objects from text, image, or sketch, without the need for manual artist intervention. We present both qualitative and quantitative results on various object categories, demonstrating the effectiveness of our approach.

Streaming Detection of Queried Event Start

Robotics, autonomous driving, augmented reality, and many embodied computer vision applications must quickly react to user-defined events unfolding in real time. We address this setting by proposing a novel task for multimodal video understanding-Streaming Detection of Queried Event Start (SDQES). The goal of SDQES is to identify the beginning of a complex event as described by a natural language query, with high accuracy and low latency. We introduce a new benchmark based on the Ego4D dataset, as well as new task-specific metrics to study streaming multimodal detection of diverse events in an egocentric video setting. Inspired by parameter-efficient fine-tuning methods in NLP and for video tasks, we propose adapter-based baselines that enable image-to-video transfer learning, allowing for efficient online video modeling. We evaluate three vision-language backbones and three adapter architectures on both short-clip and untrimmed video settings.

LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models

Open-universe 3D layout generation arranges unlabeled 3D assets conditioned on language instruction. Large language models (LLMs) struggle with generating physically plausible 3D scenes and adherence to input instructions, particularly in cluttered scenes. We introduce LayoutVLM, a framework and scene layout representation that exploits the semantic knowledge of Vision-Language Models (VLMs) and supports differentiable optimization to ensure physical plausibility. LayoutVLM employs VLMs to generate two mutually reinforcing representations from visually marked images, and a self-consistent decoding process to improve VLMs spatial planning. Our experiments show that LayoutVLM addresses the limitations of existing LLM and constraint-based approaches, producing physically plausible 3D layouts better aligned with the semantic intent of input language instructions. We also demonstrate that fine-tuning VLMs with the proposed scene layout representation extracted from existing scene datasets can improve performance.

Diffusion Self-Distillation for Zero-Shot Customized Image Generation

Text-to-image diffusion models produce impressive results but are frustrating tools for artists who desire fine-grained control. For example, a common use case is to create images of a specific instance in novel contexts, i.e., "identity-preserving generation". This setting, along with many other tasks (e.g., relighting), is a natural fit for image+text-conditional generative models. However, there is insufficient high-quality paired data to train such a model directly. We propose Diffusion Self-Distillation, a method for using a pre-trained text-to-image model to generate its own dataset for text-conditioned image-to-image tasks. We first leverage a text-to-image diffusion model's in-context generation ability to create grids of images and curate a large paired dataset with the help of a Visual-Language Model. We then fine-tune the text-to-image model into a text+image-to-image model using the curated paired dataset. We demonstrate that Diffusion Self-Distillation outperforms existing zero-shot methods and is competitive with per-instance tuning techniques on a wide range of identity-preservation generation tasks, without requiring test-time optimization.

Lifting Motion to the 3D World via 2D Diffusion

Estimating 3D motion from 2D observations is a long-standing research challenge. Prior work typically requires training on datasets containing ground truth 3D motions, limiting their applicability to activities well-represented in existing motion capture data. This dependency particularly hinders generalization to out-of-distribution scenarios or subjects where collecting 3D ground truth is challenging, such as complex athletic movements or animal motion. We introduce MVLift, a novel approach to predict global 3D motion -- including both joint rotations and root trajectories in the world coordinate system -- using only 2D pose sequences for training. Our multi-stage framework leverages 2D motion diffusion models to progressively generate consistent 2D pose sequences across multiple views, a key step in recovering accurate global 3D motion. MVLift generalizes across various domains, including human poses, human-object interactions, and animal poses. Despite not requiring 3D supervision, it outperforms prior work on five datasets, including those methods that require 3D supervision.

IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos

Shape assembly is a ubiquitous task in daily life, integral for constructing complex 3D structures like IKEA furniture. While significant progress has been made in developing autonomous agents for shape assembly, existing datasets have not yet tackled the 4D grounding of assembly instructions in videos, essential for a holistic understanding of assembly in 3D space over time. We introduce IKEA Video Manuals, a dataset that features 3D models of furniture parts, instructional manuals, assembly videos from the Internet, and most importantly, annotations of dense spatio-temporal alignments between these data modalities. To demonstrate the utility of IKEA Video Manuals, we present five applications essential for shape assembly: assembly plan generation, part-conditioned segmentation, part-conditioned pose estimation, video object segmentation, and furniture assembly based on instructional video manuals. For each application, we provide evaluation metrics and baseline methods. Through experiments on our annotated data, we highlight many challenges in grounding assembly instructions in videos to improve shape assembly, including handling occlusions, varying viewpoints, and extended assembly sequences.

HourVideo: 1-Hour Video-Language Understanding

We present HourVideo, a benchmark dataset for hour-long video-language understanding. Our dataset consists of a novel task suite comprising summarization, perception (recall, tracking), visual reasoning (spatial, temporal, predictive, causal, counterfactual), and navigation (room-to-room, object retrieval) tasks. HourVideo includes 500 manually curated egocentric videos from the Ego4D dataset, spanning durations of 20 to 120 minutes, and features 12,976 high-quality, five-way multiple-choice questions. Benchmarking results reveal that multimodal models, including GPT-4 and LLaVA-NeXT, achieve marginal improvements over random chance. In stark contrast, human experts significantly outperform the state-of-the-art long-context multimodal model, Gemini Pro 1.5 (85.0% vs. 37.3%), highlighting a substantial gap in multimodal capabilities. Our benchmark, evaluation toolkit, prompts, and documentation are available at https://hourvideo.stanford.edu

The Scene Language: Representing Scenes with Programs, Words, and Embeddings

We introduce the Scene Language, a visual scene representation that concisely and precisely describes the structure, semantics, and identity of visual scenes. It represents a scene with three key components: a program that specifies the hierarchical and relational structure of entities in the scene, words in natural language that summarize the semantic class of each entity, and embeddings that capture the visual identity of each entity. This representation can be inferred from pre-trained language models via a training-free inference technique, given text or image inputs. The resulting scene can be rendered into images using traditional, neural, or hybrid graphics renderers. Together, this forms a robust, automated system for high-quality 3D and 4D scene generation. Compared with existing representations like scene graphs, our proposed Scene Language generates complex scenes with higher fidelity, while explicitly modeling the scene structures to enable precise control and editing.

Learning Smooth Humanoid Locomotion through Lipschitz-Constrained Policies

Reinforcement learning combined with sim-to-real transfer offers a general framework for developing locomotion controllers for legged robots. To facilitate successful deployment in the real world, smoothing techniques, such as low-pass filters and smoothness rewards, are often employed to develop policies with smooth behaviors. However, because these techniques are non-differentiable and usually require tedious tuning of a large set of hyperparameters, they tend to require extensive manual tuning for each robotic platform. To address this challenge and establish a general technique for enforcing smooth behaviors, we propose a simple and effective method that imposes a Lipschitz constraint on a learned policy, which we refer to as Lipschitz-Constrained Policies (LCP). We show that the Lipschitz constraint can be implemented in the form of a gradient penalty, which provides a differentiable objective that can be easily incorporated with automatic differentiation frameworks. We demonstrate that LCP effectively replaces the need for smoothing rewards or low-pass filters and can be easily integrated into training frameworks for many distinct humanoid robots. We extensively evaluate LCP in both simulation and real-world humanoid robots, producing smooth and robust locomotion controllers. All simulation and deployment code, along with complete checkpoints, is available on our project page: https://lipschitz-constrained-policy.github.io.