Matthias Nießner

Davide Cozzolino, Alessandro Pianese, Matthias Nießner et al.

Face manipulation technology is advancing very rapidly, and new methods are being proposed day by day. The aim of this work is to propose a deepfake detector that can cope with the wide variety of manipulation methods and scenarios encountered in the real world. Our key insight is that each person has specific characteristics that a synthetic generator likely cannot reproduce. Accordingly, we extract audio-visual features which characterize the identity of a person, and use them to create a person-of-interest (POI) deepfake detector. We leverage a contrastive learning paradigm to learn the moving-face and audio segment embeddings that are most discriminative for each identity. As a result, when the video and/or audio of a person is manipulated, its representation in the embedding space becomes inconsistent with the real identity, allowing reliable detection. Training is carried out exclusively on real talking-face video; thus, the detector does not depend on any specific manipulation method and yields the highest generalization ability. In addition, our method can detect both single-modality (audio-only, video-only) and multi-modality (audio-video) attacks, and is robust to low-quality or corrupted videos. Experiments on a wide variety of datasets confirm that our method ensures a SOTA performance, especially on low quality videos. Code is publicly available on-line at https://github.com/grip-unina/poi-forensics.

Di Chang, Aljaž Božič, Tong Zhang et al.

Finding accurate correspondences among different views is the Achilles' heel of unsupervised Multi-View Stereo (MVS). Existing methods are built upon the assumption that corresponding pixels share similar photometric features. However, multi-view images in real scenarios observe non-Lambertian surfaces and experience occlusions. In this work, we propose a novel approach with neural rendering (RC-MVSNet) to solve such ambiguity issues of correspondences among views. Specifically, we impose a depth rendering consistency loss to constrain the geometry features close to the object surface to alleviate occlusions. Concurrently, we introduce a reference view synthesis loss to generate consistent supervision, even for non-Lambertian surfaces. Extensive experiments on DTU and Tanks\&Temples benchmarks demonstrate that our RC-MVSNet approach achieves state-of-the-art performance over unsupervised MVS frameworks and competitive performance to many supervised methods.The code is released at https://github.com/Boese0601/RC-MVSNet

Artem Sevastopolsky, Yury Malkov, Nikita Durasov et al.

State-of-the-art face recognition systems require vast amounts of labeled training data. Given the priority of privacy in face recognition applications, the data is limited to celebrity web crawls, which have issues such as limited numbers of identities. On the other hand, self-supervised revolution in the industry motivates research on the adaptation of related techniques to facial recognition. One of the most popular practical tricks is to augment the dataset by the samples drawn from generative models while preserving the identity. We show that a simple approach based on fine-tuning pSp encoder for StyleGAN allows us to improve upon the state-of-the-art facial recognition and performs better compared to training on synthetic face identities. We also collect large-scale unlabeled datasets with controllable ethnic constitution -- AfricanFaceSet-5M (5 million images of different people) and AsianFaceSet-3M (3 million images of different people) -- and we show that pretraining on each of them improves recognition of the respective ethnicities (as well as others), while combining all unlabeled datasets results in the biggest performance increase. Our self-supervised strategy is the most useful with limited amounts of labeled training data, which can be beneficial for more tailored face recognition tasks and when facing privacy concerns. Evaluation is based on a standard RFW dataset and a new large-scale RB-WebFace benchmark. The code and data are made publicly available at https://github.com/seva100/stylegan-for-facerec.

Davide Cozzolino, Giovanni Poggi, Matthias Nießner et al.

Detecting AI-generated images has become an extraordinarily difficult challenge as new generative architectures emerge on a daily basis with more and more capabilities and unprecedented realism. New versions of many commercial tools, such as DALLE, Midjourney, and Stable Diffusion, have been released recently, and it is impractical to continually update and retrain supervised forensic detectors to handle such a large variety of models. To address this challenge, we propose a zero-shot entropy-based detector (ZED) that neither needs AI-generated training data nor relies on knowledge of generative architectures to artificially synthesize their artifacts. Inspired by recent works on machine-generated text detection, our idea is to measure how surprising the image under analysis is compared to a model of real images. To this end, we rely on a lossless image encoder that estimates the probability distribution of each pixel given its context. To ensure computational efficiency, the encoder has a multi-resolution architecture and contexts comprise mostly pixels of the lower-resolution version of the image.Since only real images are needed to learn the model, the detector is independent of generator architectures and synthetic training data. Using a single discriminative feature, the proposed detector achieves state-of-the-art performance. On a wide variety of generative models it achieves an average improvement of more than 3% over the SoTA in terms of accuracy. Code is available at https://grip-unina.github.io/ZED/.

Kevis-Kokitsi Maninis, Stefan Popov, Matthias Nießner et al.

We propose a method for annotating videos of complex multi-object scenes with a globally-consistent 3D representation of the objects. We annotate each object with a CAD model from a database, and place it in the 3D coordinate frame of the scene with a 9-DoF pose transformation. Our method is semi-automatic and works on commonly-available RGB videos, without requiring a depth sensor. Many steps are performed automatically, and the tasks performed by humans are simple, well-specified, and require only limited reasoning in 3D. This makes them feasible for crowd-sourcing and has allowed us to construct a large-scale dataset by annotating real-estate videos from YouTube. Our dataset CAD-Estate offers 101k instances of 12k unique CAD models placed in the 3D representations of 20k videos. In comparison to Scan2CAD, the largest existing dataset with CAD model annotations on real scenes, CAD-Estate has 7x more instances and 4x more unique CAD models. We showcase the benefits of pre-training a Mask2CAD model on CAD-Estate for the task of automatic 3D object reconstruction and pose estimation, demonstrating that it leads to performance improvements on the popular Scan2CAD benchmark. The dataset is available at https://github.com/google-research/cad-estate.

Chandan Yeshwanth, Yueh-Cheng Liu, Matthias Nießner et al.

We present ScanNet++, a large-scale dataset that couples together capture of high-quality and commodity-level geometry and color of indoor scenes. Each scene is captured with a high-end laser scanner at sub-millimeter resolution, along with registered 33-megapixel images from a DSLR camera, and RGB-D streams from an iPhone. Scene reconstructions are further annotated with an open vocabulary of semantics, with label-ambiguous scenarios explicitly annotated for comprehensive semantic understanding. ScanNet++ enables a new real-world benchmark for novel view synthesis, both from high-quality RGB capture, and importantly also from commodity-level images, in addition to a new benchmark for 3D semantic scene understanding that comprehensively encapsulates diverse and ambiguous semantic labeling scenarios. Currently, ScanNet++ contains 460 scenes, 280,000 captured DSLR images, and over 3.7M iPhone RGBD frames.

Jiemin Fang, Taoran Yi, Xinggang Wang et al.

Neural radiance fields (NeRF) have shown great success in modeling 3D scenes and synthesizing novel-view images. However, most previous NeRF methods take much time to optimize one single scene. Explicit data structures, e.g. voxel features, show great potential to accelerate the training process. However, voxel features face two big challenges to be applied to dynamic scenes, i.e. modeling temporal information and capturing different scales of point motions. We propose a radiance field framework by representing scenes with time-aware voxel features, named as TiNeuVox. A tiny coordinate deformation network is introduced to model coarse motion trajectories and temporal information is further enhanced in the radiance network. A multi-distance interpolation method is proposed and applied on voxel features to model both small and large motions. Our framework significantly accelerates the optimization of dynamic radiance fields while maintaining high rendering quality. Empirical evaluation is performed on both synthetic and real scenes. Our TiNeuVox completes training with only 8 minutes and 8-MB storage cost while showing similar or even better rendering performance than previous dynamic NeRF methods.

Lukas Höllein, Ang Cao, Andrew Owens et al.

We present Text2Room, a method for generating room-scale textured 3D meshes from a given text prompt as input. To this end, we leverage pre-trained 2D text-to-image models to synthesize a sequence of images from different poses. In order to lift these outputs into a consistent 3D scene representation, we combine monocular depth estimation with a text-conditioned inpainting model. The core idea of our approach is a tailored viewpoint selection such that the content of each image can be fused into a seamless, textured 3D mesh. More specifically, we propose a continuous alignment strategy that iteratively fuses scene frames with the existing geometry to create a seamless mesh. Unlike existing works that focus on generating single objects or zoom-out trajectories from text, our method generates complete 3D scenes with multiple objects and explicit 3D geometry. We evaluate our approach using qualitative and quantitative metrics, demonstrating it as the first method to generate room-scale 3D geometry with compelling textures from only text as input.

Dave Zhenyu Chen, Yawar Siddiqui, Hsin-Ying Lee et al.

We present Text2Tex, a novel method for generating high-quality textures for 3D meshes from the given text prompts. Our method incorporates inpainting into a pre-trained depth-aware image diffusion model to progressively synthesize high resolution partial textures from multiple viewpoints. To avoid accumulating inconsistent and stretched artifacts across views, we dynamically segment the rendered view into a generation mask, which represents the generation status of each visible texel. This partitioned view representation guides the depth-aware inpainting model to generate and update partial textures for the corresponding regions. Furthermore, we propose an automatic view sequence generation scheme to determine the next best view for updating the partial texture. Extensive experiments demonstrate that our method significantly outperforms the existing text-driven approaches and GAN-based methods.

Ryan Po, Wang Yifan, Vladislav Golyanik et al.

The field of visual computing is rapidly advancing due to the emergence of generative artificial intelligence (AI), which unlocks unprecedented capabilities for the generation, editing, and reconstruction of images, videos, and 3D scenes. In these domains, diffusion models are the generative AI architecture of choice. Within the last year alone, the literature on diffusion-based tools and applications has seen exponential growth and relevant papers are published across the computer graphics, computer vision, and AI communities with new works appearing daily on arXiv. This rapid growth of the field makes it difficult to keep up with all recent developments. The goal of this state-of-the-art report (STAR) is to introduce the basic mathematical concepts of diffusion models, implementation details and design choices of the popular Stable Diffusion model, as well as overview important aspects of these generative AI tools, including personalization, conditioning, inversion, among others. Moreover, we give a comprehensive overview of the rapidly growing literature on diffusion-based generation and editing, categorized by the type of generated medium, including 2D images, videos, 3D objects, locomotion, and 4D scenes. Finally, we discuss available datasets, metrics, open challenges, and social implications. This STAR provides an intuitive starting point to explore this exciting topic for researchers, artists, and practitioners alike.

Norman Müller, Yawar Siddiqui, Lorenzo Porzi et al.

We introduce DiffRF, a novel approach for 3D radiance field synthesis based on denoising diffusion probabilistic models. While existing diffusion-based methods operate on images, latent codes, or point cloud data, we are the first to directly generate volumetric radiance fields. To this end, we propose a 3D denoising model which directly operates on an explicit voxel grid representation. However, as radiance fields generated from a set of posed images can be ambiguous and contain artifacts, obtaining ground truth radiance field samples is non-trivial. We address this challenge by pairing the denoising formulation with a rendering loss, enabling our model to learn a deviated prior that favours good image quality instead of trying to replicate fitting errors like floating artifacts. In contrast to 2D-diffusion models, our model learns multi-view consistent priors, enabling free-view synthesis and accurate shape generation. Compared to 3D GANs, our diffusion-based approach naturally enables conditional generation such as masked completion or single-view 3D synthesis at inference time.

Yawar Siddiqui, Antonio Alliegro, Alexey Artemov et al.

We introduce MeshGPT, a new approach for generating triangle meshes that reflects the compactness typical of artist-created meshes, in contrast to dense triangle meshes extracted by iso-surfacing methods from neural fields. Inspired by recent advances in powerful large language models, we adopt a sequence-based approach to autoregressively generate triangle meshes as sequences of triangles. We first learn a vocabulary of latent quantized embeddings, using graph convolutions, which inform these embeddings of the local mesh geometry and topology. These embeddings are sequenced and decoded into triangles by a decoder, ensuring that they can effectively reconstruct the mesh. A transformer is then trained on this learned vocabulary to predict the index of the next embedding given previous embeddings. Once trained, our model can be autoregressively sampled to generate new triangle meshes, directly generating compact meshes with sharp edges, more closely imitating the efficient triangulation patterns of human-crafted meshes. MeshGPT demonstrates a notable improvement over state of the art mesh generation methods, with a 9% increase in shape coverage and a 30-point enhancement in FID scores across various categories.

Yawar Siddiqui, Lorenzo Porzi, Samuel Rota Buló et al.

We propose Panoptic Lifting, a novel approach for learning panoptic 3D volumetric representations from images of in-the-wild scenes. Once trained, our model can render color images together with 3D-consistent panoptic segmentation from novel viewpoints. Unlike existing approaches which use 3D input directly or indirectly, our method requires only machine-generated 2D panoptic segmentation masks inferred from a pre-trained network. Our core contribution is a panoptic lifting scheme based on a neural field representation that generates a unified and multi-view consistent, 3D panoptic representation of the scene. To account for inconsistencies of 2D instance identifiers across views, we solve a linear assignment with a cost based on the model's current predictions and the machine-generated segmentation masks, thus enabling us to lift 2D instances to 3D in a consistent way. We further propose and ablate contributions that make our method more robust to noisy, machine-generated labels, including test-time augmentations for confidence estimates, segment consistency loss, bounded segmentation fields, and gradient stopping. Experimental results validate our approach on the challenging Hypersim, Replica, and ScanNet datasets, improving by 8.4, 13.8, and 10.6% in scene-level PQ over state of the art.

Ziya Erkoç, Fangchang Ma, Qi Shan et al.

Implicit neural fields, typically encoded by a multilayer perceptron (MLP) that maps from coordinates (e.g., xyz) to signals (e.g., signed distances), have shown remarkable promise as a high-fidelity and compact representation. However, the lack of a regular and explicit grid structure also makes it challenging to apply generative modeling directly on implicit neural fields in order to synthesize new data. To this end, we propose HyperDiffusion, a novel approach for unconditional generative modeling of implicit neural fields. HyperDiffusion operates directly on MLP weights and generates new neural implicit fields encoded by synthesized MLP parameters. Specifically, a collection of MLPs is first optimized to faithfully represent individual data samples. Subsequently, a diffusion process is trained in this MLP weight space to model the underlying distribution of neural implicit fields. HyperDiffusion enables diffusion modeling over a implicit, compact, and yet high-fidelity representation of complex signals across 3D shapes and 4D mesh animations within one single unified framework.

Shentong Mo, Enze Xie, Ruihang Chu et al.

Recent Diffusion Transformers (e.g., DiT) have demonstrated their powerful effectiveness in generating high-quality 2D images. However, it is still being determined whether the Transformer architecture performs equally well in 3D shape generation, as previous 3D diffusion methods mostly adopted the U-Net architecture. To bridge this gap, we propose a novel Diffusion Transformer for 3D shape generation, namely DiT-3D, which can directly operate the denoising process on voxelized point clouds using plain Transformers. Compared to existing U-Net approaches, our DiT-3D is more scalable in model size and produces much higher quality generations. Specifically, the DiT-3D adopts the design philosophy of DiT but modifies it by incorporating 3D positional and patch embeddings to adaptively aggregate input from voxelized point clouds. To reduce the computational cost of self-attention in 3D shape generation, we incorporate 3D window attention into Transformer blocks, as the increased 3D token length resulting from the additional dimension of voxels can lead to high computation. Finally, linear and devoxelization layers are used to predict the denoised point clouds. In addition, our transformer architecture supports efficient fine-tuning from 2D to 3D, where the pre-trained DiT-2D checkpoint on ImageNet can significantly improve DiT-3D on ShapeNet. Experimental results on the ShapeNet dataset demonstrate that the proposed DiT-3D achieves state-of-the-art performance in high-fidelity and diverse 3D point cloud generation. In particular, our DiT-3D decreases the 1-Nearest Neighbor Accuracy of the state-of-the-art method by 4.59 and increases the Coverage metric by 3.51 when evaluated on Chamfer Distance.

Jiapeng Tang, Yinyu Nie, Lev Markhasin et al.

We present DiffuScene for indoor 3D scene synthesis based on a novel scene configuration denoising diffusion model. It generates 3D instance properties stored in an unordered object set and retrieves the most similar geometry for each object configuration, which is characterized as a concatenation of different attributes, including location, size, orientation, semantics, and geometry features. We introduce a diffusion network to synthesize a collection of 3D indoor objects by denoising a set of unordered object attributes. Unordered parametrization simplifies and eases the joint distribution approximation. The shape feature diffusion facilitates natural object placements, including symmetries. Our method enables many downstream applications, including scene completion, scene arrangement, and text-conditioned scene synthesis. Experiments on the 3D-FRONT dataset show that our method can synthesize more physically plausible and diverse indoor scenes than state-of-the-art methods. Extensive ablation studies verify the effectiveness of our design choice in scene diffusion models.

Biao Zhang, Matthias Nießner, Peter Wonka

We propose a new representation for encoding 3D shapes as neural fields. The representation is designed to be compatible with the transformer architecture and to benefit both shape reconstruction and shape generation. Existing works on neural fields are grid-based representations with latents defined on a regular grid. In contrast, we define latents on irregular grids, enabling our representation to be sparse and adaptive. In the context of shape reconstruction from point clouds, our shape representation built on irregular grids improves upon grid-based methods in terms of reconstruction accuracy. For shape generation, our representation promotes high-quality shape generation using auto-regressive probabilistic models. We show different applications that improve over the current state of the art. First, we show results for probabilistic shape reconstruction from a single higher resolution image. Second, we train a probabilistic model conditioned on very low resolution images. Third, we apply our model to category-conditioned generation. All probabilistic experiments confirm that we are able to generate detailed and high quality shapes to yield the new state of the art in generative 3D shape modeling.

Yawar Siddiqui, Justus Thies, Fangchang Ma et al.

Texture cues on 3D objects are key to compelling visual representations, with the possibility to create high visual fidelity with inherent spatial consistency across different views. Since the availability of textured 3D shapes remains very limited, learning a 3D-supervised data-driven method that predicts a texture based on the 3D input is very challenging. We thus propose Texturify, a GAN-based method that leverages a 3D shape dataset of an object class and learns to reproduce the distribution of appearances observed in real images by generating high-quality textures. In particular, our method does not require any 3D color supervision or correspondence between shape geometry and images to learn the texturing of 3D objects. Texturify operates directly on the surface of the 3D objects by introducing face convolutional operators on a hierarchical 4-RoSy parametrization to generate plausible object-specific textures. Employing differentiable rendering and adversarial losses that critique individual views and consistency across views, we effectively learn the high-quality surface texturing distribution from real-world images. Experiments on car and chair shape collections show that our approach outperforms state of the art by an average of 22% in FID score.

Norman Müller, Andrea Simonelli, Lorenzo Porzi et al.

We introduce AutoRF - a new approach for learning neural 3D object representations where each object in the training set is observed by only a single view. This setting is in stark contrast to the majority of existing works that leverage multiple views of the same object, employ explicit priors during training, or require pixel-perfect annotations. To address this challenging setting, we propose to learn a normalized, object-centric representation whose embedding describes and disentangles shape, appearance, and pose. Each encoding provides well-generalizable, compact information about the object of interest, which is decoded in a single-shot into a new target view, thus enabling novel view synthesis. We further improve the reconstruction quality by optimizing shape and appearance codes at test time by fitting the representation tightly to the input image. In a series of experiments, we show that our method generalizes well to unseen objects, even across different datasets of challenging real-world street scenes such as nuScenes, KITTI, and Mapillary Metropolis.

Dave Zhenyu Chen, Ronghang Hu, Xinlei Chen et al.

Performing 3D dense captioning and visual grounding requires a common and shared understanding of the underlying multimodal relationships. However, despite some previous attempts on connecting these two related tasks with highly task-specific neural modules, it remains understudied how to explicitly depict their shared nature to learn them simultaneously. In this work, we propose UniT3D, a simple yet effective fully unified transformer-based architecture for jointly solving 3D visual grounding and dense captioning. UniT3D enables learning a strong multimodal representation across the two tasks through a supervised joint pre-training scheme with bidirectional and seq-to-seq objectives. With a generic architecture design, UniT3D allows expanding the pre-training scope to more various training sources such as the synthesized data from 2D prior knowledge to benefit 3D vision-language tasks. Extensive experiments and analysis demonstrate that UniT3D obtains significant gains for 3D dense captioning and visual grounding.

Shivangi Aneja, Justus Thies, Angela Dai et al.

We propose ClipFace, a novel self-supervised approach for text-guided editing of textured 3D morphable model of faces. Specifically, we employ user-friendly language prompts to enable control of the expressions as well as appearance of 3D faces. We leverage the geometric expressiveness of 3D morphable models, which inherently possess limited controllability and texture expressivity, and develop a self-supervised generative model to jointly synthesize expressive, textured, and articulated faces in 3D. We enable high-quality texture generation for 3D faces by adversarial self-supervised training, guided by differentiable rendering against collections of real RGB images. Controllable editing and manipulation are given by language prompts to adapt texture and expression of the 3D morphable model. To this end, we propose a neural network that predicts both texture and expression latent codes of the morphable model. Our model is trained in a self-supervised fashion by exploiting differentiable rendering and losses based on a pre-trained CLIP model. Once trained, our model jointly predicts face textures in UV-space, along with expression parameters to capture both geometry and texture changes in facial expressions in a single forward pass. We further show the applicability of our method to generate temporally changing textures for a given animation sequence.

Simon Giebenhain, Tobias Kirschstein, Markos Georgopoulos et al.

We propose a novel 3D morphable model for complete human heads based on hybrid neural fields. At the core of our model lies a neural parametric representation that disentangles identity and expressions in disjoint latent spaces. To this end, we capture a person's identity in a canonical space as a signed distance field (SDF), and model facial expressions with a neural deformation field. In addition, our representation achieves high-fidelity local detail by introducing an ensemble of local fields centered around facial anchor points. To facilitate generalization, we train our model on a newly-captured dataset of over 5200 head scans from 255 different identities using a custom high-end 3D scanning setup. Our dataset significantly exceeds comparable existing datasets, both with respect to quality and completeness of geometry, averaging around 3.5M mesh faces per scan. Finally, we demonstrate that our approach outperforms state-of-the-art methods in terms of fitting error and reconstruction quality.

Ruihang Chu, Enze Xie, Shentong Mo et al.

We introduce a new diffusion-based approach for shape completion on 3D range scans. Compared with prior deterministic and probabilistic methods, we strike a balance between realism, multi-modality, and high fidelity. We propose DiffComplete by casting shape completion as a generative task conditioned on the incomplete shape. Our key designs are two-fold. First, we devise a hierarchical feature aggregation mechanism to inject conditional features in a spatially-consistent manner. So, we can capture both local details and broader contexts of the conditional inputs to control the shape completion. Second, we propose an occupancy-aware fusion strategy in our model to enable the completion of multiple partial shapes and introduce higher flexibility on the input conditions. DiffComplete sets a new SOTA performance (e.g., 40% decrease on l_1 error) on two large-scale 3D shape completion benchmarks. Our completed shapes not only have a realistic outlook compared with the deterministic methods but also exhibit high similarity to the ground truths compared with the probabilistic alternatives. Further, DiffComplete has strong generalizability on objects of entirely unseen classes for both synthetic and real data, eliminating the need for model re-training in various applications.

Ananta R. Bhattarai, Matthias Nießner, Artem Sevastopolsky

Recent progress in NeRF-based GANs has introduced a number of approaches for high-resolution and high-fidelity generative modeling of human heads with a possibility for novel view rendering. At the same time, one must solve an inverse problem to be able to re-render or modify an existing image or video. Despite the success of universal optimization-based methods for 2D GAN inversion, those applied to 3D GANs may fail to extrapolate the result onto the novel view, whereas optimization-based 3D GAN inversion methods are time-consuming and can require at least several minutes per image. Fast encoder-based techniques, such as those developed for StyleGAN, may also be less appealing due to the lack of identity preservation. Our work introduces a fast technique that bridges the gap between the two approaches by directly utilizing the tri-plane representation presented for the EG3D generative model. In particular, we build upon a feed-forward convolutional encoder for the latent code and extend it with a fully-convolutional predictor of tri-plane numerical offsets. The renderings are similar in quality to the ones produced by optimization-based techniques and outperform the ones by encoder-based methods. As we empirically prove, this is a consequence of directly operating in the tri-plane space, not in the GAN parameter space, while making use of an encoder-based trainable approach. Finally, we demonstrate significantly more correct embedding of a face image in 3D than for all the baselines, further strengthened by a probably symmetric prior enabled during training.

Davide Cozzolino, Giovanni Poggi, Riccardo Corvi et al.

The aim of this work is to explore the potential of pre-trained vision-language models (VLMs) for universal detection of AI-generated images. We develop a lightweight detection strategy based on CLIP features and study its performance in a wide variety of challenging scenarios. We find that, contrary to previous beliefs, it is neither necessary nor convenient to use a large domain-specific dataset for training. On the contrary, by using only a handful of example images from a single generative model, a CLIP-based detector exhibits surprising generalization ability and high robustness across different architectures, including recent commercial tools such as Dalle-3, Midjourney v5, and Firefly. We match the state-of-the-art (SoTA) on in-distribution data and significantly improve upon it in terms of generalization to out-of-distribution data (+6% AUC) and robustness to impaired/laundered data (+13%). Our project is available at https://grip-unina.github.io/ClipBased-SyntheticImageDetection/

Tobias Kirschstein, Simon Giebenhain, Matthias Nießner

DiffusionAvatars synthesizes a high-fidelity 3D head avatar of a person, offering intuitive control over both pose and expression. We propose a diffusion-based neural renderer that leverages generic 2D priors to produce compelling images of faces. For coarse guidance of the expression and head pose, we render a neural parametric head model (NPHM) from the target viewpoint, which acts as a proxy geometry of the person. Additionally, to enhance the modeling of intricate facial expressions, we condition DiffusionAvatars directly on the expression codes obtained from NPHM via cross-attention. Finally, to synthesize consistent surface details across different viewpoints and expressions, we rig learnable spatial features to the head's surface via TriPlane lookup in NPHM's canonical space. We train DiffusionAvatars on RGB videos and corresponding fitted NPHM meshes of a person and test the obtained avatars in both self-reenactment and animation scenarios. Our experiments demonstrate that DiffusionAvatars generates temporally consistent and visually appealing videos for novel poses and expressions of a person, outperforming existing approaches.

Lukas Höllein, Aljaž Božič, Michael Zollhöfer et al.

We present 3DGS-LM, a new method that accelerates the reconstruction of 3D Gaussian Splatting (3DGS) by replacing its ADAM optimizer with a tailored Levenberg-Marquardt (LM). Existing methods reduce the optimization time by decreasing the number of Gaussians or by improving the implementation of the differentiable rasterizer. However, they still rely on the ADAM optimizer to fit Gaussian parameters of a scene in thousands of iterations, which can take up to an hour. To this end, we change the optimizer to LM that runs in conjunction with the 3DGS differentiable rasterizer. For efficient GPU parallization, we propose a caching data structure for intermediate gradients that allows us to efficiently calculate Jacobian-vector products in custom CUDA kernels. In every LM iteration, we calculate update directions from multiple image subsets using these kernels and combine them in a weighted mean. Overall, our method is 20% faster than the original 3DGS while obtaining the same reconstruction quality. Our optimization is also agnostic to other methods that acclerate 3DGS, thus enabling even faster speedups compared to vanilla 3DGS.

Quan Meng, Lei Li, Matthias Nießner et al.

We present LT3SD, a novel latent diffusion model for large-scale 3D scene generation. Recent advances in diffusion models have shown impressive results in 3D object generation, but are limited in spatial extent and quality when extended to 3D scenes. To generate complex and diverse 3D scene structures, we introduce a latent tree representation to effectively encode both lower-frequency geometry and higher-frequency detail in a coarse-to-fine hierarchy. We can then learn a generative diffusion process in this latent 3D scene space, modeling the latent components of a scene at each resolution level. To synthesize large-scale scenes with varying sizes, we train our diffusion model on scene patches and synthesize arbitrary-sized output 3D scenes through shared diffusion generation across multiple scene patches. Through extensive experiments, we demonstrate the efficacy and benefits of LT3SD for large-scale, high-quality unconditional 3D scene generation and for probabilistic completion for partial scene observations.

Yinyu Nie, Angela Dai, Xiaoguang Han et al.

Holistic 3D scene understanding entails estimation of both layout configuration and object geometry in a 3D environment. Recent works have shown advances in 3D scene estimation from various input modalities (e.g., images, 3D scans), by leveraging 3D supervision (e.g., 3D bounding boxes or CAD models), for which collection at scale is expensive and often intractable. To address this shortcoming, we propose a new method to learn 3D scene priors of layout and shape without requiring any 3D ground truth. Instead, we rely on 2D supervision from multi-view RGB images. Our method represents a 3D scene as a latent vector, from which we can progressively decode to a sequence of objects characterized by their class categories, 3D bounding boxes, and meshes. With our trained autoregressive decoder representing the scene prior, our method facilitates many downstream applications, including scene synthesis, interpolation, and single-view reconstruction. Experiments on 3D-FRONT and ScanNet show that our method outperforms state of the art in single-view reconstruction, and achieves state-of-the-art results in scene synthesis against baselines which require for 3D supervision.

Jiapeng Tang, Lev Markhasin, Bi Wang et al.

We present Neural Shape Deformation Priors, a novel method for shape manipulation that predicts mesh deformations of non-rigid objects from user-provided handle movements. State-of-the-art methods cast this problem as an optimization task, where the input source mesh is iteratively deformed to minimize an objective function according to hand-crafted regularizers such as ARAP. In this work, we learn the deformation behavior based on the underlying geometric properties of a shape, while leveraging a large-scale dataset containing a diverse set of non-rigid deformations. Specifically, given a source mesh and desired target locations of handles that describe the partial surface deformation, we predict a continuous deformation field that is defined in 3D space to describe the space deformation. To this end, we introduce transformer-based deformation networks that represent a shape deformation as a composition of local surface deformations. It learns a set of local latent codes anchored in 3D space, from which we can learn a set of continuous deformation functions for local surfaces. Our method can be applied to challenging deformations and generalizes well to unseen deformations. We validate our approach in experiments using the DeformingThing4D dataset, and compare to both classic optimization-based and recent neural network-based methods.

Barbara Roessle, Norman Müller, Lorenzo Porzi et al.

Neural Radiance Fields (NeRF) have shown impressive novel view synthesis results; nonetheless, even thorough recordings yield imperfections in reconstructions, for instance due to poorly observed areas or minor lighting changes. Our goal is to mitigate these imperfections from various sources with a joint solution: we take advantage of the ability of generative adversarial networks (GANs) to produce realistic images and use them to enhance realism in 3D scene reconstruction with NeRFs. To this end, we learn the patch distribution of a scene using an adversarial discriminator, which provides feedback to the radiance field reconstruction, thus improving realism in a 3D-consistent fashion. Thereby, rendering artifacts are repaired directly in the underlying 3D representation by imposing multi-view path rendering constraints. In addition, we condition a generator with multi-resolution NeRF renderings which is adversarially trained to further improve rendering quality. We demonstrate that our approach significantly improves rendering quality, e.g., nearly halving LPIPS scores compared to Nerfacto while at the same time improving PSNR by 1.4dB on the advanced indoor scenes of Tanks and Temples.

Barbara Roessle, Matthias Nießner

Erroneous feature matches have severe impact on subsequent camera pose estimation and often require additional, time-costly measures, like RANSAC, for outlier rejection. Our method tackles this challenge by addressing feature matching and pose optimization jointly. To this end, we propose a graph attention network to predict image correspondences along with confidence weights. The resulting matches serve as weighted constraints in a differentiable pose estimation. Training feature matching with gradients from pose optimization naturally learns to down-weight outliers and boosts pose estimation on image pairs compared to SuperGlue by 6.7% on ScanNet. At the same time, it reduces the pose estimation time by over 50% and renders RANSAC iterations unnecessary. Moreover, we integrate information from multiple views by spanning the graph across multiple frames to predict the matches all at once. Multi-view matching combined with end-to-end training improves the pose estimation metrics on Matterport3D by 18.5% compared to SuperGlue.

Ji Hou, Xiaoliang Dai, Zijian He et al.

Current popular backbones in computer vision, such as Vision Transformers (ViT) and ResNets are trained to perceive the world from 2D images. However, to more effectively understand 3D structural priors in 2D backbones, we propose Mask3D to leverage existing large-scale RGB-D data in a self-supervised pre-training to embed these 3D priors into 2D learned feature representations. In contrast to traditional 3D contrastive learning paradigms requiring 3D reconstructions or multi-view correspondences, our approach is simple: we formulate a pre-text reconstruction task by masking RGB and depth patches in individual RGB-D frames. We demonstrate the Mask3D is particularly effective in embedding 3D priors into the powerful 2D ViT backbone, enabling improved representation learning for various scene understanding tasks, such as semantic segmentation, instance segmentation and object detection. Experiments show that Mask3D notably outperforms existing self-supervised 3D pre-training approaches on ScanNet, NYUv2, and Cityscapes image understanding tasks, with an improvement of +6.5% mIoU against the state-of-the-art Pri3D on ScanNet image semantic segmentation.

Abdullah Hamdi, Bernard Ghanem, Matthias Nießner

Recent advances in Neural Radiance Fields (NeRFs) treat the problem of novel view synthesis as Sparse Radiance Field (SRF) optimization using sparse voxels for efficient and fast rendering (plenoxels,InstantNGP). In order to leverage machine learning and adoption of SRFs as a 3D representation, we present SPARF, a large-scale ShapeNet-based synthetic dataset for novel view synthesis consisting of $\sim$ 17 million images rendered from nearly 40,000 shapes at high resolution (400 X 400 pixels). The dataset is orders of magnitude larger than existing synthetic datasets for novel view synthesis and includes more than one million 3D-optimized radiance fields with multiple voxel resolutions. Furthermore, we propose a novel pipeline (SuRFNet) that learns to generate sparse voxel radiance fields from only few views. This is done by using the densely collected SPARF dataset and 3D sparse convolutions. SuRFNet employs partial SRFs from few/one images and a specialized SRF loss to learn to generate high-quality sparse voxel radiance fields that can be rendered from novel views. Our approach achieves state-of-the-art results in the task of unconstrained novel view synthesis based on few views on ShapeNet as compared to recent baselines. The SPARF dataset is made public with the code and models on the project website https://abdullahamdi.com/sparf/ .

Can Gümeli, Angela Dai, Matthias Nießner

We present ObjectMatch, a semantic and object-centric camera pose estimator for RGB-D SLAM pipelines. Modern camera pose estimators rely on direct correspondences of overlapping regions between frames; however, they cannot align camera frames with little or no overlap. In this work, we propose to leverage indirect correspondences obtained via semantic object identification. For instance, when an object is seen from the front in one frame and from the back in another frame, we can provide additional pose constraints through canonical object correspondences. We first propose a neural network to predict such correspondences on a per-pixel level, which we then combine in our energy formulation with state-of-the-art keypoint matching solved with a joint Gauss-Newton optimization. In a pairwise setting, our method improves registration recall of state-of-the-art feature matching, including from 24% to 45% in pairs with 10% or less inter-frame overlap. In registering RGB-D sequences, our method outperforms cutting-edge SLAM baselines in challenging, low-frame-rate scenarios, achieving more than 35% reduction in trajectory error in multiple scenes.

Dave Zhenyu Chen, Haoxuan Li, Hsin-Ying Lee et al.

We propose SceneTex, a novel method for effectively generating high-quality and style-consistent textures for indoor scenes using depth-to-image diffusion priors. Unlike previous methods that either iteratively warp 2D views onto a mesh surface or distillate diffusion latent features without accurate geometric and style cues, SceneTex formulates the texture synthesis task as an optimization problem in the RGB space where style and geometry consistency are properly reflected. At its core, SceneTex proposes a multiresolution texture field to implicitly encode the mesh appearance. We optimize the target texture via a score-distillation-based objective function in respective RGB renderings. To further secure the style consistency across views, we introduce a cross-attention decoder to predict the RGB values by cross-attending to the pre-sampled reference locations in each instance. SceneTex enables various and accurate texture synthesis for 3D-FRONT scenes, demonstrating significant improvements in visual quality and prompt fidelity over the prior texture generation methods.

Peter Kocsis, Peter Súkeník, Guillem Brasó et al.

Convolutional neural networks were the standard for solving many computer vision tasks until recently, when Transformers of MLP-based architectures have started to show competitive performance. These architectures typically have a vast number of weights and need to be trained on massive datasets; hence, they are not suitable for their use in low-data regimes. In this work, we propose a simple yet effective framework to improve generalization from small amounts of data. We augment modern CNNs with fully-connected (FC) layers and show the massive impact this architectural change has in low-data regimes. We further present an online joint knowledge-distillation method to utilize the extra FC layers at train time but avoid them during test time. This allows us to improve the generalization of a CNN-based model without any increase in the number of weights at test time. We perform classification experiments for a large range of network backbones and several standard datasets on supervised learning and active learning. Our experiments significantly outperform the networks without fully-connected layers, reaching a relative improvement of up to $16\%$ validation accuracy in the supervised setting without adding any extra parameters during inference.

Denys Rozumnyi, Stefan Popov, Kevis-Kokitsi Maninis et al.

Indoor rooms are among the most common use cases in 3D scene understanding. Current state-of-the-art methods for this task are driven by large annotated datasets. Room layouts are especially important, consisting of structural elements in 3D, such as wall, floor, and ceiling. However, they are difficult to annotate, especially on pure RGB video. We propose a novel method to produce generic 3D room layouts just from 2D segmentation masks, which are easy to annotate for humans. Based on these 2D annotations, we automatically reconstruct 3D plane equations for the structural elements and their spatial extent in the scene, and connect adjacent elements at the appropriate contact edges. We annotate and publicly release 2246 3D room layouts on the RealEstate10k dataset, containing YouTube videos. We demonstrate the high quality of these 3D layouts annotations with extensive experiments.

Angela Dai, Matthias Nießner

Implicit neural field generating signed distance field representations (SDFs) of 3D shapes have shown remarkable progress in 3D shape reconstruction and generation. We introduce a new paradigm for neural field representations of 3D scenes; rather than characterizing surfaces as SDFs, we propose a Poisson-inspired characterization for surfaces as indicator functions optimized by neural fields. Crucially, for reconstruction of real scan data, the indicator function representation enables simple and effective constraints based on common range sensing inputs, which indicate empty space based on line of sight. Such empty space information is intrinsic to the scanning process, and incorporating this knowledge enables more accurate surface reconstruction. We show that our approach demonstrates state-of-the-art reconstruction performance on both synthetic and real scanned 3D scene data, with 9.5% improvement in Chamfer distance over state of the art.

Junwen Huang, Alexey Artemov, Yujin Chen et al.

Most deep learning approaches to comprehensive semantic modeling of 3D indoor spaces require costly dense annotations in the 3D domain. In this work, we explore a central 3D scene modeling task, namely, semantic scene reconstruction without using any 3D annotations. The key idea of our approach is to design a trainable model that employs both incomplete 3D reconstructions and their corresponding source RGB-D images, fusing cross-domain features into volumetric embeddings to predict complete 3D geometry, color, and semantics with only 2D labeling which can be either manual or machine-generated. Our key technical innovation is to leverage differentiable rendering of color and semantics to bridge 2D observations and unknown 3D space, using the observed RGB images and 2D semantics as supervision, respectively. We additionally develop a learning pipeline and corresponding method to enable learning from imperfect predicted 2D labels, which could be additionally acquired by synthesizing in an augmented set of virtual training views complementing the original real captures, enabling more efficient self-supervision loop for semantics. As a result, our end-to-end trainable solution jointly addresses geometry completion, colorization, and semantic mapping from limited RGB-D images, without relying on any 3D ground-truth information. Our method achieves the state-of-the-art performance of semantic scene completion on two large-scale benchmark datasets MatterPort3D and ScanNet, surpasses baselines even with costly 3D annotations in predicting both geometry and semantics. To our knowledge, our method is also the first 2D-driven method addressing completion and semantic segmentation of real-world 3D scans simultaneously.

Dominik Schmauser, Zeju Qiu, Norman Müller et al.

We propose a novel approach for joint 3D multi-object tracking and reconstruction from RGB-D sequences in indoor environments. To this end, we detect and reconstruct objects in each frame while predicting dense correspondences mappings into a normalized object space. We leverage those correspondences to inform a graph neural network to solve for the optimal, temporally-consistent 7-DoF pose trajectories of all objects. The novelty of our method is two-fold: first, we propose a new graph-based approach for differentiable pose estimation over time to learn optimal pose trajectories; second, we present a joint formulation of reconstruction and pose estimation along the time axis for robust and geometrically consistent multi-object tracking. In order to validate our approach, we introduce a new synthetic dataset comprising 2381 unique indoor sequences with a total of 60k rendered RGB-D images for multi-object tracking with moving objects and camera positions derived from the synthetic 3D-FRONT dataset. We demonstrate that our method improves the accumulated MOTA score for all test sequences by 24.8% over existing state-of-the-art methods. In several ablations on synthetic and real-world sequences, we show that our graph-based, fully end-to-end-learnable approach yields a significant boost in tracking performance.

Natalia Soboleva, Olga Gorbunova, Maria Ivanova et al.

Surface reconstruction with preservation of geometric features is a challenging computer vision task. Despite significant progress in implicit shape reconstruction, state-of-the-art mesh extraction methods often produce aliased, perceptually distorted surfaces and lack scalability to high-resolution 3D shapes. We present a data-driven approach for automatic feature detection and remeshing that requires only a coarse, aliased mesh as input and scales to arbitrary resolution reconstructions. We define and learn a collection of surface-based fields to (1) capture sharp geometric features in the shape with an implicit vertexwise model and (2) approximate improvements in normals alignment obtained by applying edge-flips with an edgewise model. To support scaling to arbitrary complexity shapes, we learn our fields using local triangulated patches, fusing estimates on complete surface meshes. Our feature remeshing algorithm integrates the learned fields as sharp feature priors and optimizes vertex placement and mesh connectivity for maximum expected surface improvement. On a challenging collection of high-resolution shape reconstructions in the ABC dataset, our algorithm improves over state-of-the-art by 26% normals F-score and 42% perceptual $\text{RMSE}_{\text{v}}$.

Katharina Schmid, Nicolas von Lützow, Jozef Hladký et al.

We introduce a new approach to high-fidelity 3D scene reconstruction from multi-view RGB images that tightly couples reconstruction with a strong generative 3D prior. We cast scene reconstruction as conditional 3D generation over a set of spatially-localized, overlapping chunks that together tile the scene, scaling generation to large scene extents. Crucially, we inherit the fidelity and completeness of state-of-the-art generative shape models -- we use Trellis.2 as an example -- which we generalize to the scene level. To this end, we propose a projection-based conditioning mechanism that lifts posed multi-view image features into a coherent 3D representation aligned with the generative model, independent of view ordering and spatially anchored to the scene, yielding high-fidelity, multi-view consistent generated geometry. This enables lifting the strong object-level prior of Trellis.2 to multi-view, scene-scale generation, producing faithful, editable PBR mesh reconstructions of indoor environments. As a result, we obtain high-fidelity results that outperform cutting-edge reconstruction methods by 16%.

Xianzheng Ma, Brandon Smart, Yash Bhalgat et al. · bytedance, oxford

As large language models (LLMs) evolve, their integration with 3D spatial data (3D-LLMs) has seen rapid progress, offering unprecedented capabilities for understanding and interacting with physical spaces. This survey provides a comprehensive overview of the methodologies enabling LLMs to process, understand, and generate 3D data. Highlighting the unique advantages of LLMs, such as in-context learning, step-by-step reasoning, open-vocabulary capabilities, and extensive world knowledge, we underscore their potential to significantly advance spatial comprehension and interaction within embodied Artificial Intelligence (AI) systems. Our investigation spans various 3D data representations, from point clouds to Neural Radiance Fields (NeRFs). It examines their integration with LLMs for tasks such as 3D scene understanding, captioning, question-answering, and dialogue, as well as LLM-based agents for spatial reasoning, planning, and navigation. The paper also includes a brief review of other methods that integrate 3D and language. The meta-analysis presented in this paper reveals significant progress yet underscores the necessity for novel approaches to harness the full potential of 3D-LLMs. Hence, with this paper, we aim to chart a course for future research that explores and expands the capabilities of 3D-LLMs in understanding and interacting with the complex 3D world. To support this survey, we have established a project page where papers related to our topic are organized and listed: https://github.com/ActiveVisionLab/Awesome-LLM-3D.

Paul Ungermann, Armin Ettenhofer, Matthias Nießner et al.

3D Gaussian Splatting has shown impressive novel view synthesis results; nonetheless, it is vulnerable to dynamic objects polluting the input data of an otherwise static scene, so called distractors. Distractors have severe impact on the rendering quality as they get represented as view-dependent effects or result in floating artifacts. Our goal is to identify and ignore such distractors during the 3D Gaussian optimization to obtain a clean reconstruction. To this end, we take a self-supervised approach that looks at the image residuals during the optimization to determine areas that have likely been falsified by a distractor. In addition, we leverage a pretrained segmentation network to provide object awareness, enabling more accurate exclusion of distractors. This way, we obtain segmentation masks of distractors to effectively ignore them in the loss formulation. We demonstrate that our approach is robust to various distractors and strongly improves rendering quality on distractor-polluted scenes, improving PSNR by 1.86dB compared to 3D Gaussian Splatting.

Jiapeng Tang, Kai Li, Chengxiang Yin et al. · eth-zurich

We introduce FactorPortrait, a video diffusion method for controllable portrait animation that enables lifelike synthesis from disentangled control signals of facial expressions, head movement, and camera viewpoints. Given a single portrait image, a driving video, and camera trajectories, our method animates the portrait by transferring facial expressions and head movements from the driving video while simultaneously enabling novel view synthesis from arbitrary viewpoints. We utilize a pre-trained image encoder to extract facial expression latents from the driving video as control signals for animation generation. Such latents implicitly capture nuanced facial expression dynamics with identity and pose information disentangled, and they are efficiently injected into the video diffusion transformer through our proposed expression controller. For camera and head pose control, we employ Plücker ray maps and normal maps rendered from 3D body mesh tracking. To train our model, we curate a large-scale synthetic dataset containing diverse combinations of camera viewpoints, head poses, and facial expression dynamics. Extensive experiments demonstrate that our method outperforms existing approaches in realism, expressiveness, control accuracy, and view consistency.

Tobias Kirschstein, Simon Giebenhain, Matthias Nießner

We introduce FlexAvatar, a method for creating high-quality and complete 3D head avatars from a single image. A core challenge lies in the limited availability of multi-view data and the tendency of monocular training to yield incomplete 3D head reconstructions. We identify the root cause of this issue as the entanglement between driving signal and target viewpoint when learning from monocular videos. To address this, we propose a transformer-based 3D portrait animation model with learnable data source tokens, so-called bias sinks, which enables unified training across monocular and multi-view datasets. This design leverages the strengths of both data sources during inference: strong generalization from monocular data and full 3D completeness from multi-view supervision. Furthermore, our training procedure yields a smooth latent avatar space that facilitates identity interpolation and flexible fitting to an arbitrary number of input observations. In extensive evaluations on single-view, few-shot, and monocular avatar creation tasks, we verify the efficacy of FlexAvatar. Many existing methods struggle with view extrapolation while FlexAvatar generates complete 3D head avatars with realistic facial animations. Website: https://tobias-kirschstein.github.io/flexavatar/

Simon Giebenhain, Tobias Kirschstein, Liam Schoneveld et al.

Neural Parametric Head Models (NPHMs) are a recent advancement over mesh-based 3d morphable models (3DMMs) to facilitate high-fidelity geometric detail. However, fitting NPHMs to visual inputs is notoriously challenging due to the expressive nature of their underlying latent space. To this end, we propose Pix2NPHM, a vision transformer (ViT) network that directly regresses NPHM parameters, given a single image as input. Compared to existing approaches, the neural parametric space allows our method to reconstruct more recognizable facial geometry and accurate facial expressions. For broad generalization, we exploit domain-specific ViTs as backbones, which are pretrained on geometric prediction tasks. We train Pix2NPHM on a mixture of 3D data, including a total of over 100K NPHM registrations that enable direct supervision in SDF space, and large-scale 2D video datasets, for which normal estimates serve as pseudo ground truth geometry. Pix2NPHM not only allows for 3D reconstructions at interactive frame rates, it is also possible to improve geometric fidelity by a subsequent inference-time optimization against estimated surface normals and canonical point maps. As a result, we achieve unprecedented face reconstruction quality that can run at scale on in-the-wild data.

Jinxin Ai, Matthias Nießner, Ziya Erkoç

While 2D diffusion models have achieved remarkable success in identity-preserving personalization, extending this capability to 3D assets remains a significant challenge due to the complexities of multi-view consistency and spatial control. Inspired by these 2D advancements, we present a novel personalization method for text-guided 3D editing that enables compositional, object-level control through natural language. Given a 3D input, we render orthogonal views and extract object-level segmentation masks to isolate semantic components. We then learn distinct token embeddings for each component through a tailored two-phase optimization strategy: multi-view textual inversion with attention alignment, followed by full fine-tuning of multi-view diffusion model. During inference, these disentangled tokens seamlessly compose with editing prompts to generate multi-view consistent images, which are subsequently lifted into high-fidelity textured 3D meshes. Extensive evaluations across diverse editing scenarios demonstrate that our method successfully transfers the flexibility of 2D personalization to 3D, achieving state-of-the-art edit faithfulness and identity preservation compared to existing baselines.

Antonio Oroz, Matthias Nießner, Tobias Kirschstein

We present PercHead, a method for single-image 3D head reconstruction and semantic 3D editing - two tasks that are inherently challenging due to severe view occlusions, weak perceptual supervision, and the ambiguity of editing in 3D space. We develop a unified base model for reconstructing view-consistent 3D heads from a single input image. The model employs a dual-branch encoder followed by a ViT-based decoder that lifts 2D features into 3D space through iterative cross-attention. Rendering is performed using Gaussian Splatting. At the heart of our approach is a novel perceptual supervision strategy based on DINOv2 and SAM2.1, which provides rich, generalized signals for both geometric and appearance fidelity. Our model achieves state-of-the-art performance in novel-view synthesis and, furthermore, exhibits exceptional robustness to extreme viewing angles compared to established baselines. Furthermore, this base model can be seamlessly extended for semantic 3D editing by swapping the encoder and finetuning the network. In this variant, we disentangle geometry and style through two distinct input modalities: a segmentation map to control geometry and either a text prompt or a reference image to specify appearance. We highlight the intuitive and powerful 3D editing capabilities of our model through a lightweight, interactive GUI, where users can effortlessly sculpt geometry by drawing segmentation maps and stylize appearance via natural language or image prompts. Project Page: https://antoniooroz.github.io/PercHead Video: https://www.youtube.com/watch?v=4hFybgTk4kE