VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control

Modern text-to-video synthesis models demonstrate coherent, photorealistic generation of complex videos from a text description. However, most existing models lack fine-grained control over camera movement, which is critical for downstream applications related to content creation, visual effects, and 3D vision. Recently, new methods demonstrate the ability to generate videos with controllable camera poses these techniques leverage pre-trained U-Net-based diffusion models that explicitly disentangle spatial and temporal generation. Still, no existing approach enables camera control for new, transformer-based video diffusion models that process spatial and temporal information jointly. Here, we propose to tame video transformers for 3D camera control using a ControlNet-like conditioning mechanism that incorporates spatiotemporal camera embeddings based on Plucker coordinates. The approach demonstrates state-of-the-art performance for controllable video generation after fine-tuning on the RealEstate10K dataset. To the best of our knowledge, our work is the first to enable camera control for transformer-based video diffusion models.

Controlling Space and Time with Diffusion Models

We present 4DiM, a cascaded diffusion model for 4D novel view synthesis (NVS), conditioned on one or more images of a general scene, and a set of camera poses and timestamps. To overcome challenges due to limited availability of 4D training data, we advocate joint training on 3D (with camera pose), 4D (pose+time) and video (time but no pose) data and propose a new architecture that enables the same. We further advocate the calibration of SfM posed data using monocular metric depth estimators for metric scale camera control. For model evaluation, we introduce new metrics to enrich and overcome shortcomings of current evaluation schemes, demonstrating state-of-the-art results in both fidelity and pose control compared to existing diffusion models for 3D NVS, while at the same time adding the ability to handle temporal dynamics. 4DiM is also used for improved panorama stitching, pose-conditioned video to video translation, and several other tasks. For an overview see https://4d-diffusion.github.io

SpotlessSplats: Ignoring Distractors in 3D Gaussian Splatting

3D Gaussian Splatting (3DGS) is a promising technique for 3D reconstruction, offering efficient training and rendering speeds, making it suitable for real-time applications.However, current methods require highly controlled environments (no moving people or wind-blown elements, and consistent lighting) to meet the inter-view consistency assumption of 3DGS. This makes reconstruction of real-world captures problematic. We present SpotlessSplats, an approach that leverages pre-trained and general-purpose features coupled with robust optimization to effectively ignore transient distractors. Our method achieves state-of-the-art reconstruction quality both visually and quantitatively, on casual captures.

BANF: Band-limited Neural Fields for Levels of Detail Reconstruction

Largely due to their implicit nature, neural fields lack a direct mechanism for filtering, as Fourier analysis from discrete signal processing is not directly applicable to these representations. Effective filtering of neural fields is critical to enable level-of-detail processing in downstream applications, and support operations that involve sampling the field on regular grids (e.g. marching cubes). Existing methods that attempt to decompose neural fields in the frequency domain either resort to heuristics or require extensive modifications to the neural field architecture. We show that via a simple modification, one can obtain neural fields that are low-pass filtered, and in turn show how this can be exploited to obtain a frequency decomposition of the entire signal. We demonstrate the validity of our technique by investigating level-of-detail reconstruction, and showing how coarser representations can be computed effectively.

Does Gaussian Splatting need SFM Initialization?

3D Gaussian Splatting has recently been embraced as a versatile and effective method for scene reconstruction and novel view synthesis, owing to its high-quality results and compatibility with hardware rasterization. Despite its advantages, Gaussian Splatting's reliance on high-quality point cloud initialization by Structure-from-Motion (SFM) algorithms is a significant limitation to be overcome. To this end, we investigate various initialization strategies for Gaussian Splatting and delve into how volumetric reconstructions from Neural Radiance Fields (NeRF) can be utilized to bypass the dependency on SFM data. Our findings demonstrate that random initialization can perform much better if carefully designed and that by employing a combination of improved initialization strategies and structure distillation from low-cost NeRF models, it is possible to achieve equivalent results, or at times even superior, to those obtained from SFM initialization.

3D Gaussian Splatting as Markov Chain Monte Carlo

While 3D Gaussian Splatting has recently become popular for neural rendering, current methods rely on carefully engineered cloning and splitting strategies for placing Gaussians, which does not always generalize and may lead to poor-quality renderings. In addition, for real-world scenes, they rely on a good initial point cloud to perform well. In this work, we rethink 3D Gaussians as random samples drawn from an underlying probability distribution describing the physical representation of the scene -- in other words, Markov Chain Monte Carlo (MCMC) samples. Under this view, we show that the 3D Gaussian updates are strikingly similar to a Stochastic Langevin Gradient Descent (SGLD) update. As with MCMC, samples are nothing but past visit locations, adding new Gaussians under our framework can simply be realized without heuristics as placing Gaussians at existing Gaussian locations. To encourage using fewer Gaussians for efficiency, we introduce an L1-regularizer on the Gaussians. On various standard evaluation scenes, we show that our method provides improved rendering quality, easy control over the number of Gaussians, and robustness to initialization.

TC4D: Trajectory-Conditioned Text-to-4D Generation

Recent techniques for text-to-4D generation synthesize dynamic 3D scenes using supervision from pre-trained text-to-video models. However, existing representations for motion, such as deformation models or time-dependent neural representations, are limited in the amount of motion they can generate-they cannot synthesize motion extending far beyond the bounding box used for volume rendering. The lack of a more flexible motion model contributes to the gap in realism between 4D generation methods and recent, near-photorealistic video generation models. Here, we propose TC4D: trajectory-conditioned text-to-4D generation, which factors motion into global and local components. We represent the global motion of a scene's bounding box using rigid transformation along a trajectory parameterized by a spline. We learn local deformations that conform to the global trajectory using supervision from a text-to-video model. Our approach enables the synthesis of scenes animated along arbitrary trajectories, compositional scene generation, and significant improvements to the realism and amount of generated motion, which we evaluate qualitatively and through a user study. Video results can be viewed on our website: https://sherwinbahmani.github.io/tc4d.

pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction

We introduce pixelSplat, a feed-forward model that learns to reconstruct 3D radiance fields parameterized by 3D Gaussian primitives from pairs of images. Our model features real-time and memory-efficient rendering for scalable training as well as fast 3D reconstruction at inference time. To overcome local minima inherent to sparse and locally supported representations, we predict a dense probability distribution over 3D and sample Gaussian means from that probability distribution. We make this sampling operation differentiable via a reparameterization trick, allowing us to back-propagate gradients through the Gaussian splatting representation. We benchmark our method on wide-baseline novel view synthesis on the real-world RealEstate10k and ACID datasets, where we outperform state-of-the-art light field transformers and accelerate rendering by 2.5 orders of magnitude while reconstructing an interpretable and editable 3D radiance field.

Densify Your Labels: Unsupervised Clustering with Bipartite Matching for Weakly Supervised Point Cloud Segmentation

We propose a weakly supervised semantic segmentation method for point clouds that predicts "per-point" labels from just "whole-scene" annotations while achieving the performance of recent fully supervised approaches. Our core idea is to propagate the scene-level labels to each point in the point cloud by creating pseudo labels in a conservative way. Specifically, we over-segment point cloud features via unsupervised clustering and associate scene-level labels with clusters through bipartite matching, thus propagating scene labels only to the most relevant clusters, leaving the rest to be guided solely via unsupervised clustering. We empirically demonstrate that over-segmentation and bipartite assignment plays a crucial role. We evaluate our method on ScanNet and S3DIS datasets, outperforming state of the art, and demonstrate that we can achieve results comparable to fully supervised methods.

Unsupervised Keypoints from Pretrained Diffusion Models

Unsupervised learning of keypoints and landmarks has seen significant progress with the help of modern neural network architectures, but performance is yet to match the supervised counterpart, making their practicability questionable. We leverage the emergent knowledge within text-to-image diffusion models, towards more robust unsupervised keypoints. Our core idea is to find text embeddings that would cause the generative model to consistently attend to compact regions in images (i.e. keypoints). To do so, we simply optimize the text embedding such that the cross-attention maps within the denoising network are localized as Gaussians with small standard deviations. We validate our performance on multiple datasets: the CelebA, CUB-200-2011, Tai-Chi-HD, DeepFashion, and Human3.6m datasets. We achieve significantly improved accuracy, sometimes even outperforming supervised ones, particularly for data that is non-aligned and less curated. Our code is publicly available and can be found through our project page: https://ubc-vision.github.io/StableKeypoints/